pp-openipa
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill facilitates the installation of a CLI tool using 'npx' and 'go install' from the vendor's GitHub and NPM repositories. These operations involve downloading and running external code.
- [DATA_EXPOSURE_AND_EXFILTRATION]: The CLI includes a '--deliver webhook:' flag that allows command output to be sent to any external URL. This creates a potential data exfiltration vector if the tool is manipulated to send sensitive data to an unauthorized endpoint.
- [COMMAND_EXECUTION]: The skill's primary function is the execution of 'openipa-pp-cli' shell commands to query and process administrative data.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the IPA API and user-supplied files, creating a surface for indirect prompt injection. Ingestion points: Data returned from the IPA API and files like 'lista_cf.txt'. Boundary markers: No delimiters or safety instructions are provided to the agent for handling external data. Capability inventory: The CLI supports network requests, file writing, and shell command execution. Sanitization: There is no evidence of data sanitization or validation in the provided skill instructions.
Audit Metadata