project-context

Pass

Audited by Gen Agent Trust Hub on Nov 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to prioritize and execute instructions found in repository files, which creates a vulnerability surface if the repository contains malicious content.
  • Ingestion points: The agent is instructed to read TESTING.md, README.md, CONSTRAINTS.md, AGENTS.md, docs/, scripts/, and CONTRIBUTING.md.
  • Boundary markers: Absent. There are no instructions to isolate or treat content from these files as potentially untrusted data.
  • Capability inventory: The skill encourages the agent to use project-provided test commands, scripts, and custom runners, as well as to follow documented setup, environment, database, and reset rules.
  • Sanitization: Absent. There are no guidelines for validating or sanitizing commands or instructions extracted from project files before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 18, 2026, 05:34 PM