create-pull-request

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and follow project-specific PR templates, which represents an ingestion surface for untrusted data that could influence agent behavior.
  • Ingestion points: Pull request templates and file diffs gathered from the project environment (SKILL.md).
  • Boundary markers: Absent; the instructions do not explicitly tell the agent to disregard instructions embedded within external project templates.
  • Capability inventory: Utilizes host tooling for PR publication, shell interaction, and screen/terminal capture (SKILL.md).
  • Sanitization: Includes positive security practices by instructing the agent to omit session IDs, internal metadata, and pasted identifiers from the PR body.
  • [SAFE]: The skill consists entirely of instructional markdown and does not include any executable scripts, binaries, or hardcoded credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 04:18 AM
Security Audit — agent-trust-hub — create-pull-request