Skills
skills/biw/skills/detailed-pr-description/Gen Agent Trust Hub

detailed-pr-description

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local shell commands including git (status, diff, log) and gh (pr view, pr edit) to interact with the repository and GitHub API. These are standard tools for the skill's stated purpose of PR management.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8). It ingests untrusted data from the local file system, git diffs, and existing GitHub PR bodies to generate its descriptions.
  • Ingestion points: Data enters the context via gh pr view and various git commands (diff, show) in SKILL.md.
  • Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands within the ingested data.
  • Capability inventory: The agent has the capability to write files to the .context/ directory and modify GitHub PR descriptions via gh pr edit.
  • Sanitization: No explicit sanitization or validation of the ingested external content is mentioned in the workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 06:37 PM
Security Audit — agent-trust-hub — detailed-pr-description