doc-tspec-autopilot
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands and Python scripts within the project workspace. Evidence includes:
- Directory exploration using
ls docs/10_TSPEC/TSPEC-{NN}_*/to verify file structures. - Execution of a local maintenance script:
python ai_dev_ssd_flow/scripts/update_traceability_matrix.pyto synchronize document metadata. - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it is designed to ingest and process untrusted external data (SPEC, IPLAN, and TSPEC documents) while possessing capabilities to modify files and execute scripts.
- Ingestion points: Processes SPEC documents, IPLAN files, and existing TSPEC documents from the project directory.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing external file content.
- Capability inventory: File system read/write access, directory listing commands, Python script execution, and invocation of auxiliary agent tools (audit, reviewer, fixer).
- Sanitization: No explicit sanitization or validation of the natural language content within the ingested documents is defined.
Audit Metadata