Loading the registry…
Contextual blast-radius scoring for shell commands an AI agent is about to run
The publisher performed an authenticated act of publication — proving control of a namespace in the official MCP registry, or appearing in a first-party catalogue an operator curates. That establishes WHO published it. It is not a security finding, and attested artifacts carry Flagged verdicts too.
61 critical findings reported by cisco-skill-scanner, agent-audit-kit, 4 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
github: https://github.com/Atharva-Jayappa/blast-scope, 177 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- blast-scope
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
4 of 11 scanners examined this package. The rest do not apply to it — language, ecosystem and packaging decide which analyzers can say anything, and a scanner that cannot examine an artifact reports nothing rather than passing it.
v2.0.11
41 findings · 9.3s
v0.3.26
78 findings · 3.9s
v0.1.0
0 findings · 27.3s
v0.1.0
2 findings · 27.3s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.1s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image, nerlo-multi-source.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 9, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicable | rejected |
Findings in files this artifact installs stand as reported; a model re-read the rest and said which ones it believes are false positives. This is a second opinion published beside the evidence, not a correction to it: the per-scanner reports above are unchanged, every dismissed finding is still listed there at its original severity, and the score and the Flagged badge are computed from those raw severities alone. Nothing below moved them.
Out of 121 findings across every scanner that examined this package. 57 of 61 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 1 finding stand exactly as their scanners reported them, at full severity, as they would have without this review.
Two keys had to turn. The model had to name a reason from a fixed list of six, and a deterministic check of ours — over which files this artifact actually installs — had to independently agree. Anything it could not corroborate is in “not reviewed” above, at full severity.
56 Agent instruction file — The match is in a file that instructs an AI coding agent — a CLAUDE.md or similar. It is documentation of intent, and our own check confirmed it is not part of what gets installed.
Rules: AAK-AGENT-001, TOOL_ABUSE_UNDECLARED_NETWORK · Files: CLAUDE.md, /repo/repo/CLAUDE.md · reported by agent-audit-kit, cisco-skill-scanner
14 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: PIPELINE_TAINT_FLOW, opt.nerlo-rules.nerlo-install-pipe-to-shell, AAK-HEALTHCARE-AI-004 and 2 more · Files: /repo/docs/research/rung3_validity.md, /repo/docs/research/SKILL.md, /repo/docs/heuristics.md and 2 more · reported by cisco-skill-scanner, nerlo-install-instruction, agent-audit-kit
8 Test or fixture file — The match is in a test or fixture. Our own check confirmed the file is not part of what gets installed.
Rules: YARA_sql_injection_generic, COMMAND_INJECTION_OS_SYSTEM, AAK-IPI-WILD-CORPUS-001 and 1 more · Files: /repo/tests/test_security_regressions.py, /repo/tests/test_resolution.py, tests/test_classes_docker_pkg_sql.py and 5 more · reported by cisco-skill-scanner, agent-audit-kit
2 CI or editor configuration — The match is in build, CI or editor configuration, confirmed by our own check to be outside the installed artifact.
Rules: AAK-GHA-IMMUTABLE-001 · Files: .github/workflows/ci.yml, .github/workflows/rung3-pilot.yml · reported by agent-audit-kit
These findings are in files this artifact installs and are not placeholder values. No false-positive basis can be corroborated for such a finding, so this review never dismisses one; they were not sent to the model and stand at their scanner's severity.
6 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/bench/rung3_pilot/judge.py · reported by cisco-skill-scanner
4 AAK-IPI-WILD-CORPUS-001
Files: README.md, bench/saber_eval.py, src/blast_scope/command_parser.py and 1 more · reported by agent-audit-kit
4 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md, /repo/bench/SKILL.md, /repo/src/blast_scope/vendor/crg/SKILL.md and 1 more · reported by cisco-skill-scanner
4 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/bench/SKILL.md, /repo/src/blast_scope/vendor/crg/SKILL.md and 1 more · reported by cisco-skill-scanner
2 RESOURCE_ABUSE_INFINITE_LOOP
Files: /repo/src/blast_scope/vendor/crg/tsconfig_resolver.py · reported by cisco-skill-scanner
2 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/bench/repo/bench/README.md, /repo/bench/rung3_pilot/repo/bench/rung3_pilot/README.md · reported by cisco-skill-scanner
2 YARA_sql_injection_generic
Files: /repo/src/blast_scope/vendor/crg/graph.py · reported by cisco-skill-scanner
1 AAK-DNS-REBIND-002
Files: pyproject.toml · reported by agent-audit-kit
1 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
1 AAK-MCP-005
Files: .mcp.json · reported by agent-audit-kit
1 AAK-MCP-007
Files: .mcp.json · reported by agent-audit-kit
1 AAK-OAUTH-3P-001
Files: pyproject.toml · reported by agent-audit-kit
1 AAK-SEC-MD-001
Files: SECURITY.md · reported by agent-audit-kit
1 AAK-STATE-PRIVACY-001
Files: PRIVACY.md · reported by agent-audit-kit
1 AAK-STATE-PRIVACY-002
Files: PRIVACY.md · reported by agent-audit-kit
1 AAK-STATE-PRIVACY-003
Files: PRIVACY.md · reported by agent-audit-kit
1 AAK-SUPPLY-001
Files: .mcp.json · reported by agent-audit-kit
1 AAK-TASKS-003
Files: bench/saber_eval.py · reported by agent-audit-kit
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 MANIFEST_INVALID_NAME
Files: /repo/bench/rung3_pilot/SKILL.md · reported by cisco-skill-scanner
1 YARA_system_manipulation_generic
Files: /repo/src/blast_scope/speculate.py · reported by cisco-skill-scanner
The model could have called any of these a false positive and did not.
2 SQL_INJECTION_STRING_FORMAT
Files: /repo/src/blast_scope/vendor/crg/graph.py · reported by cisco-skill-scanner
1 The model did not answer for these findings.
Rules: FIND_EXEC_PATTERN · Files: /repo/docs/SKILL.md · reported by cisco-skill-scanner
Critical SQL injection and system manipulation risks identified.
The artifact contains critical SQL injection vulnerabilities in `/repo/src/blast_scope/vendor/crg/graph.py` that could allow unauthorized database access or manipulation. Additionally, a high-severity finding for system manipulation is present in `/repo/src/blast_scope/speculate.py`, indicating potential for shell execution. The artifact also includes code that could lead to resource abuse via infinite loops in `/repo/src/blast_scope/vendor/crg/tsconfig_resolver.py` and undeclared network activity.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.