skills/byronfinn/dev-skills/write/Gen Agent Trust Hub

write

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied prose and fetches data from external sources, creating a potential attack surface for indirect prompt injection.
  • Ingestion points: The skill accepts prose from the user for editing (SKILL.md) and retrieves content from GitHub issues, pull requests, and git logs using gh and git tools (REFERENCE.md).
  • Boundary markers: The instructions do not define explicit delimiters or boundary markers to isolate external data from the skill's core instructions.
  • Capability inventory: The skill utilizes command-line tools gh and git to read information from local and remote repositories to assist in writing tasks.
  • Sanitization: No mention of sanitization, filtering, or validation of the fetched or provided text is made in the skill's procedures.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 06:22 AM
Security Audit — agent-trust-hub — write