tools-p4-changelist
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on shell commands to interact with the Perforce CLI (p4). This includes operations for creating, editing, and deleting changelists, as well as administrative tasks using the -f flag to force operations or change file ownership.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and process data retrieved from a Perforce server, creating a vulnerability surface where malicious instructions in changelist descriptions could influence the agent's behavior.
- Ingestion points: Data is ingested through commands like p4 change -o, p4 describe, and p4 changes which retrieve metadata and descriptions from the server into the agent context.
- Boundary markers: There are no protective boundary markers or instructions within the skill to help the agent distinguish between data and instructions in the retrieved text.
- Capability inventory: The agent has the capability to perform significant actions like submitting code, modifying file permissions, and deleting changelists via the Perforce CLI based on processed data.
- Sanitization: The skill does not implement any validation or sanitization of the changelist descriptions before they are presented to the agent.
Audit Metadata