pr-description

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to execute local shell commands such as git diff main...HEAD to collect the data necessary for generating descriptions. This is a primary function of the skill.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) due to the way it processes external input.
  • Ingestion points: The agent ingests untrusted data from branch diffs as part of its primary workflow (SKILL.md, Workflow Step 1).
  • Boundary markers: The skill lacks explicit instructions or markers to distinguish between legitimate code changes and potentially malicious instructions embedded within code comments or string literals in the diff.
  • Capability inventory: The skill output is designed to include 'copy-pasteable testing instructions', creating a vector where an attacker-controlled diff could influence the agent to suggest dangerous commands to the user.
  • Sanitization: There is no evidence of sanitization or filtering of the diff content before it is used to generate the final description and testing steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 11:10 PM