blueprint-promote
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill demonstrates a vulnerability surface where untrusted user input from the command argument is directly interpolated into a shell command.
- Ingestion points: The '{name}' argument provided in the skill-name|command-name parameter.
- Boundary markers: Absent; the input is placed directly into the shell string '.claude/rules/{name}.md' without delimiters or safety warnings.
- Capability inventory: The skill is permitted to use 'Bash', 'Read', and 'Write' tools, enabling file system modification and command execution.
- Sanitization: Absent; the instructions do not require the agent to validate, escape, or sanitize the 'name' variable before executing the 'test -f' command.
Audit Metadata