pipa-time-tracking

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill processes time-tracking record data from an external API, which represents an indirect prompt injection surface.
  • Ingestion points: Data is retrieved from the Pipa API via the /v1/agent-utility-records endpoint (SKILL.md).
  • Boundary markers: The instructions do not define specific delimiters or warnings to prevent the agent from interpreting instructions that might be embedded within record fields like titles or notes.
  • Capability inventory: The skill has capabilities to perform network requests and write to the local file system for credential storage.
  • Sanitization: No sanitization or validation of the retrieved record content is specified before it is presented to the user or processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with an external API gateway at pailflow-chat-gateway.fly.dev for managing time-tracking records and performing email-based authentication.
  • [COMMAND_EXECUTION]: The skill accesses the local file system to manage its own configuration, specifically targeting the .pipa/credentials file in the workspace root and the user's home directory. It includes instructions to set secure file permissions (mode 600) for these files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 09:02 PM
Security Audit — agent-trust-hub — pipa-time-tracking