plot-idea
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill constructs shell commands using user-supplied input from the title field. This input is placed directly into commands like
git commit -m "plot: <title>"andgh pr create --title "Plan: <title>"without sanitization, which could lead to command injection if malicious shell characters are provided. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests data from the project's local environment which may be influenced by external sources.
- Ingestion points: Reads configuration from
CLAUDE.mdand file lists fromdocs/plans/. - Boundary markers: Absent; no delimiters or instructions are used to ignore embedded commands in the processed data.
- Capability inventory: Performs git operations (
git fetch,git checkout,git commit,git push), GitHub CLI operations (gh pr create,gh pr edit), and filesystem operations (mkdir,ln,cat,date) withinSKILL.md. - Sanitization: Absent; configuration values like the project board name are used directly in commands without validation.
Audit Metadata