fundraising

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and analyze untrusted external data sources.
  • Ingestion points: The SKILL.md workflow (Step 1) explicitly directs the agent to inspect existing decks, memos, metrics, and financial models.
  • Boundary markers: The instructions lack delimiters or specific directives for the agent to ignore potentially malicious instructions embedded within these external documents.
  • Capability inventory: The skill relies on general agent capabilities; no platform tools are explicitly restricted.
  • Sanitization: There are no instructions for validating or sanitizing the content of the ingested documents.
  • [NO_CODE]: The skill is comprised solely of markdown instructions and documentation, with no executable scripts, binaries, or automated configuration changes detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 06:57 AM
Security Audit — agent-trust-hub — fundraising