doc-coauthoring

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection via its context gathering mechanism.
  • Ingestion points: Data is pulled from external files, shared document links, and team messaging channels (Slack, Teams) in Stage 1 of the workflow.
  • Boundary markers: The instructions do not define delimiters or instructions to disregard embedded commands in the ingested context.
  • Capability inventory: The skill uses tools like 'create_file' and 'str_replace' to generate content, which could be manipulated by instructions hidden in the context.
  • Sanitization: No sanitization or validation of the ingested external data is performed before it is used in prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 05:29 PM