wayfinder

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from an external issue tracker (tickets, maps, and comments) to guide its next actions, creating a surface where untrusted instructions can influence agent behavior.\n
  • Ingestion points: The agent reads issue titles, bodies, and resolution comments from the tracker, as well as external 'tracker docs' and findings retrieved by the /research subagent. It also dynamically looks up and invokes tools specified in the 'Notes' section of the map artifact.\n
  • Boundary markers: The skill lacks explicit instructions for using delimiters or 'ignore' warnings for the data ingested from the tracker, which could allow malicious content in a ticket to override agent logic.\n
  • Capability inventory: The skill can create and modify issues, trigger specialized sub-skills (/research, /prototype, /grilling, /domain-modeling), create Git branches (research/<name>), and perform 'AFK' tasks such as provisioning access or moving data.\n
  • Sanitization: There is no evidence of sanitization or validation for the content retrieved from the external tracker before it is used to influence the agent's decision-making process or tool selection.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 09:28 AM