boilerplate
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on shell scripts (bash) to perform framework detection and template substitution. It uses commands like
grep,sed,cat, andsource. - Evidence: Use of
sed "s/\${COMPONENT_NAME}/$component_name/g"andsource "$cache_file"in the optimization logic described inSKILL.md. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection or command injection because it interpolates user-provided arguments (
$ARGUMENTS) directly into shell commands without sanitization. - Ingestion points: User-supplied arguments for component/route/model names (
SKILL.md). - Boundary markers: None present to distinguish user input from executable command logic.
- Capability inventory: File system read/write, shell command execution via agent capabilities.
- Sanitization: No evidence of validation or escaping for the
$ARGUMENTSvariable before its use insedor file path construction.
Audit Metadata