stakeholder-brief

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external information and user input to generate a formatted document, creating a surface for potential indirect instructions to influence the agent.
  • Ingestion points: The skill ingests data from user responses (context, situation, asks) and external files such as system-health assessments, adoption reports, or project files (e.g., knowledge-notes/).
  • Boundary markers: It employs a five-part template and placeholders like [needs data: ...] to structure the brief, which helps maintain output format but does not include explicit instructions for the agent to ignore directives that might be embedded in the source data.
  • Capability inventory: The skill utilizes Read, Write, Grep, Glob, and scoped Bash tools (cat and ls) to gather information.
  • Sanitization: No specific sanitization, escaping, or filtering of the external content is prescribed before it is interpolated into the stakeholder brief template.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 08:20 PM