setup-matt-pocock-skills
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from repository files to generate documentation and instructions for other agents.
- Ingestion points: Reads existing repository files including
CONTEXT.md,CONTEXT-MAP.md,AGENTS.md, andCLAUDE.mdduring the 'Explore' phase. - Boundary markers: The skill does not implement explicit delimiters or instructions to the agent to ignore embedded instructions within the files it reads.
- Capability inventory: The skill has the capability to write to the file system, specifically modifying primary agent instruction files (
AGENTS.md,CLAUDE.md) and creating new documentation indocs/agents/. - Sanitization: There is no evidence of sanitization or validation of the content ingested from the repository before it is used to populate templates or written to disk.
- [DATA_EXFILTRATION]: The skill accesses the local
.git/configfile and executesgit remote -v. While this is intended to identify the repository's upstream host (e.g., GitHub or GitLab) to recommend the correct configuration, these files can potentially contain sensitive information, such as authentication tokens embedded in remote URLs.
Audit Metadata