talk-stage6-revision
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a template-driven document generator. It uses the 'Read' and 'Write' tools to aggregate content from existing local files in the 'talks/' directory and output a revision guide. There are no network operations or command execution capabilities present.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data from several ingestion points. 1. Ingestion points: pitch, slides, and concept files in the 'talks/' directory. 2. Boundary markers: None are defined to separate the instructions from the data content. 3. Capability inventory: The skill is restricted to 'Read' and 'Write' tools. 4. Sanitization: No sanitization or validation of input file content is performed. Given the limited toolset and the nature of the output (markdown files), the risk of significant harm from indirect prompt injection is minimal.
Audit Metadata