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