grant-builder

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data that could contain hidden instructions intended to manipulate the agent's behavior. Because the skill has access to tools capable of system-level operations and file modification, this represents an attack surface.
  • Ingestion points: The skill is designed to ingest and analyze external "funding call / RFP" and "project concept" documents (referenced in skill.yml and SKILL.md).
  • Boundary markers: The instructions do not specify the use of delimiters or provide warnings to the agent to ignore potentially malicious instructions embedded within the user-provided grant materials.
  • Capability inventory: The skill is configured with access to Read, Write, Edit, Bash, Grep, and Glob tools, which provides a significant capability for an attacker if the agent is successfully injected via a malicious funding call.
  • Sanitization: There is no evidence of input validation or sanitization routines for external text before it is processed by the agent's logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 01:59 AM
Security Audit — agent-trust-hub — grant-builder