fundraising-strategy

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill utilizes a validation script, scripts/check-output.py, to scan generated deliverables for required keywords. This ingestion of external data without defined boundary markers or sanitization logic creates a surface for indirect prompt injection where instructions embedded in a processed file could potentially influence agent behavior.\n
  • Ingestion points: The script scripts/check-output.py accepts a file path as a command-line argument and reads its contents.\n
  • Boundary markers: Absent. The skill does not provide instructions or delimiters to isolate embedded commands from data in the processed files.\n
  • Capability inventory: The script employs the pathlib library to access and read the contents of the target file (path.read_text).\n
  • Sanitization: No sanitization or filtering is applied to the text before the keyword validation process is executed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 03:05 AM
Security Audit — agent-trust-hub — fundraising-strategy