test-strategy-writer
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external documentation which introduces a vulnerability surface.
- Ingestion points: Document paths for PRD, API Contract, and HLD are identified via glob scanning and read during Phase 0 of the workflow to extract requirements and risks.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing content from these external files.
- Capability inventory: The skill is capable of executing local Python scripts and generating structured documents.
- Sanitization: No sanitization or validation of the content within the ingested documents is performed prior to processing.
- [COMMAND_EXECUTION]: The skill invokes local Python scripts to validate artifacts and check traceability.
- Evidence: SKILL.md includes instructions in Phase 4 to execute python3 "$TESTANY_ENG_ROOT/scripts/trace_lint.py" and python3 "$TESTANY_ENG_ROOT/scripts/trace_build_rtm.py".
- Context: These script executions are used for quality assurance purposes and target files within a vendor-controlled environment variable path.
Audit Metadata