stakeholder-adapter

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided documents (text or files) and possesses file-writing capabilities, creating an attack surface for indirect prompt injection. An adversary could include malicious instructions within a document intended for adaptation. However, the skill's instructions specifically restrict the agent from adding invented facts or commitments, and file-writing requires explicit user confirmation.
  • Ingestion points: Source documents provided via pasted text or local file paths (.md, .txt) as defined in SKILL.md under the Input section.
  • Boundary markers: Absent; the skill does not explicitly instruct the agent to use delimiters or specific ignore markers for the source content.
  • Capability inventory: File system write operations (writing .md files to the current working directory) as defined in SKILL.md Step 5.
  • Sanitization: Absent; the skill does not specify sanitization or escaping for the input document content.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 09:40 AM
Security Audit — agent-trust-hub — stakeholder-adapter