utility-slideshow-creator
Pass
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run local Node.js scripts (
scripts/generate-deck.jsandscripts/export-pdf.mjs) to render slide decks. This is the intended functionality of the skill and follows standard practices for local file generation. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted 'content briefs' into a structured JSON specification.
- Ingestion points: The content brief provided by the user (as referenced in
SKILL.md). - Boundary markers: Absent; the instructions do not specify any delimiters to separate the user-provided brief from the agent's logic.
- Capability inventory: Shell execution of Node.js scripts (as referenced in
SKILL.md). - Sanitization: No documented sanitization or validation logic for the input data or generated JSON fields (such as
outputFileName) is provided.
Audit Metadata