council-review
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local binaries
~/bin/validate-planand~/bin/reviewto perform automated validation and code reviews. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it ingests and processes external data from plans and source code during validation tasks.
- Ingestion points: Plan files located in
~/.claude/plans/and project files provided during PR reviews. - Boundary markers: Absent; the instructions do not specify the use of delimiters or ignore-instructions for the processed data.
- Capability inventory: The agent uses the
Bashtool to invoke validation and review scripts on the ingested files. - Sanitization: No sanitization or escaping of external content is mentioned in the logic.
Audit Metadata