skill-auto-update

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill establishing a mechanism for rewriting agent instructions based on external feedback, which creates a vulnerability surface for indirect prompt injection attacks.
  • Ingestion points: Reads from user turn content and external platform comments (e.g., pull requests, issues) as specified in SKILL.md.
  • Capability inventory: Logic enables the agent to modify its own skill library or create new skill files.
  • Sanitization: No evidence of validation or filtering for incoming feedback content to ensure it does not contain malicious instructions.
  • Boundary markers: The skill lacks delimiters or protective instructions to distinguish untrusted feedback from the distillation logic.
  • [NO_CODE]: This skill does not contain any executable code, scripts, or binary files; it is composed entirely of markdown instructions and YAML configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 06:08 PM