to-confluence

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local filesystem to generate documentation, creating a surface for adversarial instructions embedded in those files to influence agent behavior.
  • Ingestion points: The skill reads various project artifacts, including links, specs, and implementation notes, from the .agents/projects/ directory.
  • Boundary markers: There are no defined delimiters or specific instructions to treat ingested project data as untrusted text, increasing the risk that the agent may interpret data as commands.
  • Capability inventory: The skill has access to the local file system for drafting and context updates, and uses a Confluence MCP for network-based page updates.
  • Sanitization: The instructions do not specify any validation, escaping, or filtering for the source content before it is synthesized into the final document.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 06:37 AM
Security Audit — agent-trust-hub — to-confluence