issue-slice-prompts

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the gh CLI (gh issue view) to retrieve issue metadata and content from the specific repository SantiagoXOR/pintureria-digital. It also suggests using standard filesystem search tools like grep to explore the codebase.
  • [EXTERNAL_DOWNLOADS]: Data is fetched from an external source (GitHub). The target repository matches the author's namespace, indicating legitimate vendor-specific functionality.
  • [PROMPT_INJECTION]: The skill processes untrusted data from GitHub issue bodies, creating a surface for indirect prompt injection.
  • Ingestion points: GitHub issue content (body, title, labels) retrieved via the GitHub CLI in SKILL.md.
  • Boundary markers: The instructions do not specify explicit delimiters or warnings for the agent to ignore embedded instructions in the issue content.
  • Capability inventory: The agent has access to the shell (gh, grep) and the filesystem (read).
  • Sanitization: No sanitization or filtering of the external issue content is performed before it is used to generate the final prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 08:55 AM
Security Audit — agent-trust-hub — issue-slice-prompts