wayfinder

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external issue trackers (such as GitHub or local markdown files) to build and update a 'map' of decision tickets.
  • Ingestion points: Issue titles and bodies are read from the repo's tracker to orient the session and choose tasks.
  • Boundary markers: The instructions do not define explicit delimiters or 'ignore embedded instructions' warnings for content fetched from the issue tracker.
  • Capability inventory: The skill can create new issues, wire dependencies between them, and spin up subagents for research tasks.
  • Sanitization: There is no evidence of filtering or escaping of the external content before it is processed by the agent.
  • [COMMAND_EXECUTION]: The skill instructs the user to execute an external command if a tracker is not provided.
  • Evidence: Instructions mention running /setup-matt-pocock-skills to configure the tracker environment. While likely a domain-specific setup utility, it represents an external execution dependency.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 06:52 AM
Security Audit — agent-trust-hub — wayfinder