frontend-slides
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes OS-specific commands (open, xdg-open, start) to open the final HTML presentation in the user's browser as part of its delivery workflow. This is standard behavior for its intended purpose of creating web-based presentations.- [EXTERNAL_DOWNLOADS]: The skill recommends installing the python-pptx package to facilitate slide conversion, which involves downloading a standard package from a public registry. This dependency is necessary for the skill's primary function.- [PROMPT_INJECTION]: The skill processes user-supplied PowerPoint files (.ppt, .pptx) to extract content, which creates a potential surface for indirect prompt injection if those files contain malicious instructions aimed at influencing the agent's behavior.
- Ingestion points: User-provided PowerPoint files (.ppt, .pptx) processed by the conversion workflow in SKILL.md.
- Boundary markers: None explicitly defined to isolate untrusted content from the agent's primary instructions.
- Capability inventory: Shell command execution (file openers), local file writing, and script execution via python3.
- Sanitization: Not explicitly described for the content extracted from presentation slides.
Audit Metadata