update-doc
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's operations are confined to the
.chalk/docs/directory and it uses standard tools for reading and editing files. No network activity, sensitive data access, or code execution patterns were found.- [INDIRECT_PROMPT_INJECTION]: The skill reads and writes documentation content, which presents a surface for indirect prompt injection. - Ingestion points: Files in
.chalk/docs/are read in the Workflow Step 2. - Boundary markers: Absent; there are no delimiters used to separate documentation content from agent instructions.
- Capability inventory: The skill uses the
Edittool to modify files on the local filesystem. - Sanitization: None detected; the content is processed directly to apply updates. Given the restricted scope and intended purpose, this is considered a low-risk architectural characteristic rather than a vulnerability.
Audit Metadata