wayfinder
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill is a documented adaptation of content from a reputable public repository (github.com/mattpocock/skills.git). This source is well-known in the software development community and the reference is part of the skill's provenance and versioning metadata.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from a repository's issue tracker, creating a potential surface for indirect prompt injection if malicious instructions are embedded in issue descriptions or comments.
- Ingestion points: The skill loads issue titles, bodies, and resolution comments from the tracker to build its planning map (SKILL.md).
- Boundary markers: The skill uses markdown headers (e.g., ## Question, ## Destination) to structure data, but does not explicitly instruct the agent to ignore instructions found within those fields.
- Capability inventory: The skill uses internal tools for research, prototyping, and domain modeling, and it has permissions to create and update issues and comments.
- Sanitization: No specific sanitization or validation of the fetched issue content is described in the instructions.
Audit Metadata