static-analysis
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to execute shell commands specified in the input prompt.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface (Category 8) because it executes 'pre-computed commands' supplied in the prompt without validation.
- Ingestion points: The input prompt provides the 'Pre-computed commands' and 'Scoped file list' (SKILL.md).
- Boundary markers: Absent. The skill does not use delimiters or instructions to disregard potentially malicious instructions within the command strings.
- Capability inventory: The skill utilizes the Bash tool (SKILL.md frontmatter).
- Sanitization: Absent. The skill is instructed to run the 'exact commands' provided without modification or filtering.
Audit Metadata