vet
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell command substitution (e.g.,
$(echo "$PWD" | tr '/' '-')) to dynamically construct file paths in Phase 1. While intended for path normalization, this pattern can be susceptible to command injection if the environment variables or directory names are maliciously crafted. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it processes untrusted data from the filesystem.
- Ingestion points: Reads task descriptions and metadata from
*.vetted.jsonfiles in the~/.claude/projects/directory (SKILL.md). - Boundary markers: The instructions do not specify the use of delimiters or provide warnings to ignore embedded instructions within the processed JSON data.
- Capability inventory: The skill has access to
Bash(limited tolsandcat) andAskUserQuestion. - Sanitization: There is no evidence of content sanitization or validation of the
taskfield before the agent evaluates its clarity and completion status.
Audit Metadata