continuity-check
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructions for the agent to review and update continuity documentation within a project structure. It does not utilize any tools that interact with the network or the underlying operating system in a way that poses a security risk.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from project artifacts and rule files. While this is an attack surface for indirect prompt injection, the lack of high-risk capabilities (e.g., shell execution, network exfiltration) renders this surface safe in the current context.
- Ingestion points: Reads core contract, CONTINUITY_RULES.md, project artifacts, and 01_story/story_state.json (SKILL.md).
- Boundary markers: None identified.
- Capability inventory: Writes to 03_preproduction/continuity.md and updates story-state JSON (SKILL.md).
- Sanitization: None identified.
Audit Metadata