ctx-compact
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes session data to update source-of-truth files, creating a potential surface for indirect prompt injection.
- Ingestion points: The skill ingests "decisions" and "progress" from the current chat session context (SKILL.md).
- Boundary markers: No explicit boundary markers or delimiters for untrusted data are specified in the orchestration logic to prevent the agent from obeying instructions embedded in the session history.
- Capability inventory: The skill performs file-write operations indirectly by invoking ctx-spec and ctx-merge skills to update specifications and decision logs on disk.
- Sanitization: No explicit sanitization or validation of the session data is performed before it is passed to the destination skills for archival.
Audit Metadata