doc-tspec-reviewer
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill explicitly instructs the agent to execute bash commands including 'sha256sum', 'yq', and 'grep' to calculate hashes of SPEC and TSPEC documents. This is used for its core 'Upstream Drift Detection' feature.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it ingests and processes data from external TSPEC and SPEC files. 1. Ingestion points: The agent reads markdown and YAML documents from 'docs/10_TSPEC/' and 'docs/09_SPEC/'. 2. Boundary markers: The skill does not define delimiters or instructions to ignore embedded commands within the ingested documentation. 3. Capability inventory: The skill has the capability to execute shell commands and modify local files (e.g., .drift_cache.json). 4. Sanitization: No explicit validation or sanitization of the document content is specified.
Audit Metadata