authoring-marp-slides
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is designed for slide authoring and does not contain any obfuscated code, hardcoded credentials, or persistence mechanisms.\n- [COMMAND_EXECUTION]: The skill uses a local shell script,
scripts/check_marpit_structure.sh, to perform structural validation of Markdown files. The script is securely written using quoted variables and path normalization to prevent injection attacks.\n- [PROMPT_INJECTION]: The skill processes user-provided Markdown content for slide authoring, creating an indirect prompt injection surface. The risk is considered safe due to the limited scope of the authoring task.\n - Ingestion points: Markdown files (
deck.md) provided by the user or current project state inSKILL.mdworkflow.\n - Boundary markers: None provided in instructions to isolate user content from agent logic.\n
- Capability inventory: File system reading, file writing (authoring), and execution of local shell scripts and the
marpCLI.\n - Sanitization: The skill performs limited structural validation via
scripts/check_marpit_structure.shbut does not sanitize the actual slide content.
Audit Metadata