knowledge-docs
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and follow instructions from a user-provided manifest file (
KNOWLEDGE.md). While this provides an attack surface where adversarial content in the manifest could influence the agent's logic, this behavior is the intended primary purpose for project-level customization. - Ingestion points: The skill reads
KNOWLEDGE.mdand documentation files within a user-defined root directory. - Boundary markers: None; manifest instructions are explicitly declared as binding and override default behavior.
- Capability inventory: Reads and writes markdown files; delegates repository management (commits, PRs) to the
knowledge-githubskill. - Sanitization: None observed.
- [SAFE]: No obfuscation, data exfiltration, or unauthorized command execution was identified. The skill's operations are confined to documentation management within a local or repository context.
Audit Metadata