Skills
skills/malinskibeniamin/skills/setup-matt-pocock-skills/Gen Agent Trust Hub

setup-matt-pocock-skills

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the gh (GitHub) and glab (GitLab) command-line interfaces to perform repository management tasks such as creating, viewing, and listing issues. It also executes git remote -v to identify repository remotes.
  • [PROMPT_INJECTION]: The skill defines workflows for ingesting untrusted data from external trackers, creating a surface for indirect prompt injection.
  • Ingestion points: Untrusted data enters the context via gh issue view and glab issue view (found in issue-tracker-github.md and issue-tracker-gitlab.md).
  • Boundary markers: The instructions do not specify delimiters or "ignore" blocks for ingested content to prevent the execution of embedded instructions.
  • Capability inventory: The agent can perform subprocess calls for git, gh, and glab CLI operations and has file writing capabilities for project documentation (referenced in SKILL.md).
  • Sanitization: No sanitization or validation of remote issue content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 01:39 PM
Security Audit — agent-trust-hub — setup-matt-pocock-skills