posix-shell-pro
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill functions as a code-generation assistant for POSIX shell scripts, which creates a natural surface for indirect prompt injection via user-supplied requirements. However, the skill explicitly mitigates these risks by providing the agent with strict security instructions.\n
- Ingestion points: User-defined scripting goals and constraints processed by the agent as described in SKILL.md.\n
- Boundary markers: The instructions do not define specific delimiters for user input, though they do mandate that the agent clarify goals and constraints before script generation.\n
- Capability inventory: The generated scripts are intended for system tasks involving file operations, command execution, and resource management.\n
- Sanitization: The skill mandates input sanitization, numeric validation via case patterns, and the use of the
--delimiter to prevent argument injection attacks.\n- [SAFE]: The skill provides high-quality security guidance for shell development. It instructs the agent to quote all variable expansions to prevent word splitting, validate file permissions, and use restrictive umasks (e.g., 077) for sensitive operations. External documentation links refer exclusively to trusted or well-known technical entities including The Open Group, GNU, Debian, and the FreeBSD Project.
Audit Metadata