presentation-docs
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use standard shell utilities such as
pdftotext,pdfimages,pdftoppm, andgrepto extract content from document files. These tools are used appropriately for the skill's primary function of document conversion. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface (Category 8) because it processes untrusted text from external documents supplied by the user. Maliciously crafted content within a source document could potentially contain instructions aimed at influencing the agent's output.
- Ingestion points: Processes external document formats including PDF, PPTX, DOCX, and ODP files.
- Boundary markers: Instructions focus on structural transliteration but do not provide explicit guidance to ignore instructions embedded within the source files.
- Capability inventory: The agent is granted capabilities to read and write files, as well as execute specific shell commands for file processing.
- Sanitization: No specific sanitization or filtering of the extracted document text is detailed before it is converted to the final Markdown output.
Audit Metadata