blindspot

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill employs dynamic context injection to run git commands at load time for orientation purposes.
  • Evidence: SKILL.md contains !git branch --show-current and !git rev-parse --show-toplevel. These are used to set variables for the session and are benign.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its core function of processing external data.
  • Ingestion points: Codebase files and official documentation are read to build a 'vocabulary ladder' in SKILL.md.
  • Boundary markers: No explicit delimiters are specified for ingested content in the instructions.
  • Capability inventory: The skill is limited to reading data and coaching prompts; it does not have write access or perform dangerous system modifications.
  • Sanitization: The instructions do not specify sanitization for the content fetched from files or documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 07:55 PM
Security Audit — agent-trust-hub — blindspot