pitch

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for narrative construction and fundraising preparation. It does not initiate network connections, execute shell commands, or access sensitive system directories.
  • [PROMPT_INJECTION]: The skill utilizes a local file (innov.local.md) to provide context-aware responses, which introduces a surface for indirect prompt injection.
  • Ingestion points: The skill reads venture-specific details from innov.local.md located in the working directory.
  • Boundary markers: There are no explicit delimiters or protective instructions used when interpolating data from the context file into the agent's prompts.
  • Capability inventory: The skill lacks any dangerous tools; it cannot write files, run subprocesses, or access the network.
  • Sanitization: No input validation or filtering is applied to the content of the local configuration file.
  • Assessment: Because the skill's capabilities are restricted to text output and it has no access to sensitive data or external systems, this surface represents a negligible security risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 07:56 AM
Security Audit — agent-trust-hub — pitch