investment-risk-diligence

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted external data such as news digests and financial filings, making it susceptible to indirect prompt injection where malicious instructions could be embedded in those sources.
  • Ingestion points: External data is ingested via filings, earnings notes, financial snapshots, news digests, and market signals as described in the Inputs section of SKILL.md.
  • Boundary markers: The instructions do not define clear boundaries or 'ignore' commands to prevent the agent from following instructions embedded within these external sources.
  • Capability inventory: The skill includes instructions to write diligence notes to the local file system at research/targets/<target>/evidence/risks/ as specified in SKILL.md.
  • Sanitization: No specific sanitization or filtering logic is provided for the ingested external content before it is processed or used in file operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 10:23 PM
Security Audit — agent-trust-hub — investment-risk-diligence