wayfinder
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves ingesting and processing data from issue trackers, creating a vulnerability surface where malicious instructions could be embedded in ticket content.
- Ingestion points: The agent reads ticket bodies, questions, and investigation details from either the local
.scratch/directory (as defined inissue-tracker-local.md) or an external issue tracker specified by the user inSKILL.md. - Boundary markers: There are no instructions provided to the agent to treat ticket content as data only or to ignore potential instructions found within issue descriptions, comments, or resolution summaries.
- Capability inventory: The skill is capable of writing files to the local repository, spawning research subagents that can access information outside the current directory, and linking generated code/logic prototypes.
- Sanitization: The skill lacks explicit sanitization, escaping, or validation mechanisms for content retrieved from external trackers before it influences the agent's planning or execution logic.
Audit Metadata