partner-programs

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a local utility script scripts/check-output.py that the agent is instructed to run for validating the length and keyword presence of its generated deliverables. The script uses standard libraries and does not perform network operations or access sensitive system files.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user input related to company details and partner program requirements to populate a specific output template.
  • Ingestion points: User-provided company and program details processed in SKILL.md and templates/output-template.md to generate the partner program design.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within the user-provided data.
  • Capability inventory: The skill uses a local Python script scripts/check-output.py to validate output files.
  • Sanitization: There is no explicit sanitization or validation of the user input before it is interpolated into the final markdown deliverable.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 12:46 PM
Security Audit — agent-trust-hub — partner-programs