specs-extractor
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security risks were detected in the skill's instructions. The skill is dedicated to documenting existing software systems without performing high-risk actions like network exfiltration or credential harvesting.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from a legacy codebase (source code, tests, documentation) to generate specifications. This creates a surface for indirect prompt injection where malicious instructions embedded in the source code could attempt to influence the agent's behavior.
- Ingestion points: The skill analyzes all project files, including application code, database schemas, and documentation (Phase 0 and Source Analysis Scope).
- Boundary markers: The instructions do not define specific delimiters for separating input code from instructions, though they impose a strict output structure (Requirement/Scenario format).
- Capability inventory: The skill utilizes file system write capabilities to create or update markdown files in the
specs/directory (Phase 7 and File Output). - Sanitization: No explicit data sanitization or escaping is mentioned for the extracted content, relying on the agent's adherence to the specified format.
Audit Metadata