extract-scripts

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the creation and execution of shell scripts on the local system (e.g., 'Run ./script-name.sh'). It attempts to mitigate risk by providing detailed best practices for the AI to follow, such as resolving script directories dynamically, avoiding hardcoded absolute paths, and using 'set -euo pipefail' for error handling.
  • [PROMPT_INJECTION]: The skill processes external skill files which may contain untrusted data, creating an indirect prompt injection surface.
  • Ingestion points: Reads target skill files provided by the user (Step 1).
  • Boundary markers: None specified to differentiate between the processing logic and the content of the skill being analyzed.
  • Capability inventory: The skill can write files, modify permissions ('chmod +x'), and execute shell scripts.
  • Sanitization: No explicit sanitization or validation of the instructions being extracted from the source skill file is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 05:33 AM
Security Audit — agent-trust-hub — extract-scripts