skill-extract-scripts

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external content from other skill files, which creates a surface for indirect prompt injection where malicious instructions in the target file could influence the agent during the extraction process.
  • Ingestion points: Reads target skill files as specified in Step 1.
  • Boundary markers: Absent; the skill does not define specific delimiters or instructions to ignore embedded commands within the files it reads.
  • Capability inventory: The agent performs file reading, creation of new shell scripts, and modification of existing skill files.
  • Sanitization: Absent; there is no step involving the escaping or validation of the content being extracted from the target skill.
  • [SAFE]: The skill promotes secure and resilient DevOps practices by providing detailed instructions for writing location-independent scripts, using strict shell execution modes (set -euo pipefail), and implementing robust argument validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 08:28 PM
Security Audit — agent-trust-hub — skill-extract-scripts