context-gather
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes comprehensive session context and external session materials to generate persistent knowledge entries in the .context/ directory. \n
- Ingestion points: The skill reviews the 'whole available session and context' and uses 'imported session material' as described in SKILL.md. \n
- Boundary markers: There are no instructions for using delimiters or boundary markers to separate untrusted user-provided data from the agent's summary logic. \n
- Capability inventory: The skill uses file-writing capabilities to create, update, and index markdown files within the project's .context/ directory (SKILL.md). \n
- Sanitization: While the skill instructs the agent not to copy raw transcripts or secrets, it does not include mechanisms to filter or sanitize potential instructions embedded within the session data.
Audit Metadata