pp-pangolin
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to download and install the
pangolin-pp-cliandpangolin-pp-mcptools usingnpxandgo installfrom the@mvanhornNPM scope andgithub.com/mvanhornrepository. - [REMOTE_CODE_EXECUTION]: Installation steps involve executing code fetched directly from external repositories during the binary installation processes.
- [DATA_EXFILTRATION]: The CLI tool provides a
--deliver webhook:<url>feature and afeedbackcommand that can send data to a user-defined endpoint. These mechanisms allow configuration data, access tokens, and audit results to be sent to external servers. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the Pangolin API (e.g., resource names, user IDs, audit logs) through commands like
auditandsearch. Ingestion points includepangolin-pp-cli auditand general resource listing commands. The agent uses theBashtool to execute the CLI and manage its output, but no specific boundary markers or input sanitization are defined for the data processed by the agent.
Audit Metadata