pricing-packaging-planner
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a robust security model that prioritizes user authorization and data integrity. No malicious patterns such as prompt injection, unauthorized data exfiltration, or remote code execution were found.
- [INDIRECT_PROMPT_INJECTION]: The skill proactively addresses this risk. Both
SKILL.mdandreferences/skill-contract.mdcontain explicit instructions for the agent to treat scraped text, emails, and other external data as untrusted evidence rather than executable instructions, effectively mitigating potential injection attacks from external sources. - [CREDENTIALS_UNSAFE]: The documentation specifically advises against storing API keys in source control or skill files, promoting secure secret management practices.
- [COMMAND_EXECUTION]: The skill design limits the agent's capability to perform side effects (publishing, spending, mutating accounts) by mandating explicit user authorization for such actions, preventing unauthorized or accidental command execution.
Audit Metadata