wiki-onboarding

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes repository files (source code, build manifests such as package.json or Cargo.toml, and existing documentation) to generate its output.
  • Ingestion points: Files within the repository are accessed during the scan for build files and when tracing data flows or state from actual code.
  • Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions potentially embedded within the analyzed code (e.g., malicious comments designed to influence the guide's output).
  • Capability inventory: The skill performs repository scanning and text generation, including the production of Mermaid diagrams and Markdown documentation.
  • Sanitization: The instructions do not specify any validation or sanitization of content extracted from the files before it is interpolated into the generated guides.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 08:57 PM
Security Audit — agent-trust-hub — wiki-onboarding