prepare-pr

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on executing local shell scripts (scripts/pr-prepare, scripts/committer) and system tools like jq to perform its tasks. These scripts use input parameters like the PR number or URL which could be a vector for command injection if the input is not properly sanitized by the underlying scripts or the agent context.
  • [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection (Category 8) because it processes untrusted data from external files. 1. Ingestion points: Data is ingested from .local/review.json, specifically within the findings, changelog, and docs fields. 2. Boundary markers: The instructions lack explicit delimiters or warnings to ignore potential instructions embedded within the JSON data. 3. Capability inventory: The skill has significant capabilities, including file system writes (modifying CHANGELOG.md and documentation) and executing subprocesses for Git commits and pushes. 4. Sanitization: There is no evidence of sanitization or validation performed on the strings extracted from the JSON file before they are interpolated into the agent's workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 01:07 AM