update-spatie-docs
Fail
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: HIGHCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The bash script in SKILL.md interpolates the user-provided
{repo_name}directly into a command line:php artisan docs:import --repo=spatie/{repo_name}. This lacks sanitization, allowing an attacker to use shell metacharacters (e.g.,;,&,|) to execute arbitrary commands. - [PROMPT_INJECTION]: The skill accepts unvalidated arguments from the user to construct system commands, creating a vulnerability surface for indirect prompt injection. Ingestion point:
{repo_name}argument in SKILL.md. Boundary markers: Absent. Capability inventory: Bash subprocess execution viaphp artisan. Sanitization: Absent. - [DATA_EXPOSURE]: The skill discloses the specific local directory path
/Users/freek/dev/code/spatie.be, which reveals system-level information about the user's directory structure and username.
Recommendations
- AI detected serious security threats
Audit Metadata