skills/milistu/agent-skills/pr-review/Gen Agent Trust Hub

pr-review

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (LOW): Indirect Prompt Injection Surface. The skill's primary function is to ingest and process untrusted external data (pull request content), which exposes it to adversarial instructions designed to bypass agent constraints.\n
  • Ingestion points: The skill ingests pull request code, branch data, and ticket descriptions provided by the user (SKILL.md).\n
  • Boundary markers: Absent. There are no instructions or delimiters defined to separate the skill's core instructions from the untrusted data being analyzed.\n
  • Capability inventory: The skill is strictly instructional and focused on analysis; it does not invoke dangerous capabilities such as file-system writes, network requests, or command execution.\n
  • Sanitization: Absent. The skill does not implement any sanitization, filtering, or validation of the ingested PR content to detect or neutralize potential injection attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:29 PM