setup-agent-skills

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using git, gh (GitHub CLI), and glab (GitLab CLI) to perform repository discovery and manage issue/merge request workflows.
  • [DATA_EXFILTRATION]: The skill accesses .git/config and runs git remote -v to identify the repository's remote origin and hosting provider. While .git/config can contain repository metadata, this access is limited to discovery for setup purposes.
  • [PROMPT_INJECTION]: The skill implements a workflow for reading issue titles, bodies, and comments from GitHub, GitLab, and local markdown files. This ingestion of untrusted data from external sources creates a surface for indirect prompt injection.
  • Ingestion points: Remote issue data fetched via gh issue view --comments, glab issue view --comments, and local files under .scratch/.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified for the ingested content.
  • Capability inventory: Shell command execution (gh, glab, git) and local filesystem write operations.
  • Sanitization: No sanitization or validation of the external content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 05:19 PM
Security Audit — agent-trust-hub — setup-agent-skills