setup-matt-pocock-skills
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface identified in the configuration templates provided by the skill. The skill scaffolds files (
issue-tracker-github.mdandissue-tracker-gitlab.md) that instruct agents to fetch and process untrusted content from external contributors. - Ingestion points: The setup guides specify commands for reading issue and pull request data (e.g.,
gh issue view,gh pr view,glab issue view) which include user-controlled titles, bodies, and comments. - Boundary markers: The configuration templates do not include instructions for using delimiters or explicit "ignore" warnings when this untrusted data is interpolated into the agent's context.
- Capability inventory: The environment established by this skill allows agents to write files to the repository and execute platform CLI tools (
gh,glab) to perform actions on behalf of the user. - Sanitization: No sanitization or validation mechanisms are defined for the fetched external content to prevent malicious instructions from influencing agent behavior.
Audit Metadata