intent-keeper
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- External Content Processing (Indirect Prompt Injection): The skill is designed to analyze external project resources such as design briefs, issue trackers, and commit histories to detect goal drift.
- Ingestion points: The skill instructions specify reading from and searching through various external documents to reconstruct original project asks (SKILL.md).
- Boundary markers: The instructions do not explicitly define specific delimiters or instructions to the agent to disregard potentially malicious commands embedded within the documents it processes.
- Capability inventory: The skill's primary function is to perform analysis and provide structured feedback (PASS/CONCERN/FAIL) based on the content it reads.
- Sanitization: There are no explicit requirements mentioned for sanitizing or filtering the text extracted from external documentation.
Audit Metadata