weekly-report
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external text data from meeting logs or local files, creating a surface where instructions embedded in that data could be processed by the agent.
- Ingestion points: User-provided text or files accessed via the
Readtool as described in the 'Input Convention' section ofSKILL.md. - Boundary markers: The skill does not define specific delimiters to separate untrusted meeting text from its own instructions.
- Capability inventory: The agent utilizes the
Readtool to access file content when a path is provided by the user inSKILL.md. - Sanitization: The instructions do not specify any validation or sanitization steps for the ingested content.
Audit Metadata