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.mdworkflow (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