NYC
skills/vm0-ai/vm0-skills/pdfco/Gen Agent Trust Hub

pdfco

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • COMMAND_EXECUTION (LOW): The skill uses bash -c to execute curl commands. While this is used to ensure environment variables are correctly handled within specific runtimes, the use of shell execution for API calls is noted as a lower-tier security concern.
  • PROMPT_INJECTION (LOW): The skill possesses a surface for indirect prompt injection when processing untrusted external PDF files or HTML content via the API. Evidence Chain: 1. Ingestion points: url and html parameters within the request.json file. 2. Boundary markers: No delimiters or warnings are used to wrap the extracted text returned to the agent. 3. Capability inventory: curl commands for API interaction. 4. Sanitization: No sanitization or validation of the ingested external content is performed within the skill scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:03 PM