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-cli and pangolin-pp-mcp tools using npx and go install from the @mvanhorn NPM scope and github.com/mvanhorn repository.
  • [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 a feedback command 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 audit and search. Ingestion points include pangolin-pp-cli audit and general resource listing commands. The agent uses the Bash tool 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
Risk Level
SAFE
Analyzed
Sep 20, 2026, 09:32 PM