draft-wallhit-planner
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process draft documents, which creates a surface for indirect prompt injection if those documents contain malicious instructions.
- Ingestion points: The agent identifies and reads proposal documents from the
_docs/proposals/directory to facilitate the review process. - Boundary markers: The instructions do not define clear delimiters or use 'ignore embedded instructions' warnings when processing the draft content.
- Capability inventory: The skill's primary capabilities include reading files and writing generated review documents and logs to the local file system.
- Sanitization: The workflow does not include any steps for sanitizing, escaping, or validating the content of the external drafts before they are used in template generation.
Audit Metadata