wayfinder

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill manages its state and logic by reading content from an issue tracker, creating an attack surface where untrusted data could influence agent behavior.
  • Ingestion points: The agent is instructed to load the "map" and "ticket" bodies (which are issue descriptions and comments) from the repository's issue tracker to orient itself and perform work.
  • Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions when reading from the tracker, potentially allowing content within a ticket to override agent directives.
  • Capability inventory: The skill has the ability to invoke sub-agents for research and prototyping, create new issues, manage git branches, and modify repository metadata.
  • Sanitization: The instructions do not define any sanitization or validation steps for content retrieved from the issue tracker before it is processed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 03:08 AM
Security Audit — agent-trust-hub — wayfinder