wayfinder
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from an issue tracker to guide the agent's planning and decision-making. This creates a potential surface where malicious instructions in a ticket could influence the agent's actions.
- Ingestion points: The skill loads the map issue and child ticket bodies as context during the 'Work through the map' phase (detailed in SKILL.md).
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined for the issue content.
- Capability inventory: The skill can create, update, and close issues, as well as spin up research subagents and call external skill tools.
- Sanitization: No sanitization or validation of the ingested issue text is mentioned.
- [EXTERNAL_DOWNLOADS]: The UPSTREAM.md file contains references and commands to download or install the skill and its dependencies from external GitHub repositories. These are documented as standard deployment steps for the vendor's infrastructure.
Audit Metadata