shunk031-shellscript-shdoc-docs

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The SKILL.md file contains a directive for the agent to output a specific acknowledgement string ('🐚 I read shunk031-shellscript-shdoc-docs') after reading the instructions, which is a form of output control.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (shell scripts), which presents an attack surface for indirect prompt injection.
  • Ingestion points: Target shell scripts provided by the user or environment as specified in the Workflow section of SKILL.md.
  • Boundary markers: The skill instructions do not define delimiters or specific warnings to disregard instructions potentially embedded in the scripts being analyzed.
  • Capability inventory: The agent has the capability to read scripts and modify them by adding or repairing documentation comments (SKILL.md).
  • Sanitization: There is no specified mechanism for sanitizing or filtering the content of the shell scripts before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 04:08 AM
Security Audit — agent-trust-hub — shunk031-shellscript-shdoc-docs