pr-description-writer

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands git log and git diff to gather context about recent changes. These commands are legitimate for the skill's purpose and are used in a read-only manner.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from git logs and diffs. An attacker with the ability to commit to the repository could include malicious instructions in commit messages or code comments to manipulate the generated PR description. [1. Ingestion points]: Data retrieved from git log and git diff results in SKILL.md. [2. Boundary markers]: No explicit delimiters or markers are defined to isolate the untrusted git data from the agent's instructions. [3. Capability inventory]: The skill executes git commands and produces summarized text output. [4. Sanitization]: No validation or escaping is performed on the data ingested from the repository history.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 08:07 PM
Security Audit — agent-trust-hub — pr-description-writer