make-repo-agent-legible

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's instructions and reference files are focused on established software development best practices and repository organization. No malicious patterns, obfuscation, or unauthorized data exfiltration were detected.
  • [PROMPT_INJECTION]: The skill is designed to ingest and process entire software repositories, creating an attack surface for indirect prompt injection.
  • Ingestion points: The agent is instructed to read AGENTS.md, architecture documentation, and repository source code (SKILL.md Workflow Steps 1 and 2).
  • Boundary markers: Absent; the workflow does not specify the use of delimiters or instructions to ignore embedded prompts found within the repository files.
  • Capability inventory: The agent has capabilities for file creation (Default Deliverables) and interaction with local systems, CLIs, and logs for behavior inspection (SKILL.md Workflow Step 8).
  • Sanitization: Absent; the instructions do not describe sanitization or validation of the content read from the repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 03:28 AM
Security Audit — agent-trust-hub — make-repo-agent-legible