Skills
skills/richfrem/agent-plugins-skills/rsvp-reading/Gen Agent Trust Hub

rsvp-reading

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute local Python scripts (parse_document.py and orp_engine.py) for document parsing and RSVP token generation.\n- [EXTERNAL_DOWNLOADS]: The skill identifies dependencies on standard document processing libraries python-docx and pdfminer.six for handling DOCX and PDF file formats.\n- [PROMPT_INJECTION]: The skill processes untrusted user documents, creating an indirect prompt injection surface when the agent reviews the generated token preview or interacts with the processed text.\n
  • Ingestion points: External document content is ingested through the parse_document.py script via the --input argument.\n
  • Boundary markers: The skill does not employ specific delimiters to isolate the document content from the agent's instructions.\n
  • Capability inventory: The skill uses Bash, Read, and Write tools to perform local file operations and script execution.\n
  • Sanitization: The skill tokenizes raw text into individual words but does not sanitize or filter the content for potential malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 06:09 PM