skills/l-yifan/skills/doc-coauthoring/Gen Agent Trust Hub

doc-coauthoring

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because its core purpose is to process external, potentially untrusted data.
  • Ingestion points: The workflow explicitly pulls data from uploaded files, shared document links (Google Drive, SharePoint), and team messaging channels (Slack, Teams).
  • Boundary markers: The instructions do not mandate the use of XML delimiters or boundary markers to isolate external content from the agent's control logic.
  • Capability inventory: The agent has the capability to read external data and write/modify files using tools like create_file and str_replace.
  • Sanitization: There is no requirement for the agent to sanitize, filter, or validate instructions that might be embedded within the documents or messages being co-authored.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 08:16 AM