jam-proof-table
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the
jamcommand-line interface to interact with the Jam.dev service. It executes commands to authenticate, list folders, create recordings, and retrieve session data (console, network, and video frames). - [EXTERNAL_DOWNLOADS]: The instructions refer the user to
https://jam.dev/docs/clifor the manual installation of the required CLI tool, adhering to the principle of avoiding automated remote code execution by the agent. - [INDIRECT_PROMPT_INJECTION]: The skill represents an indirect prompt injection surface as it ingests and processes untrusted data from external Jam recordings.
- Ingestion points: Metadata, console logs, and network events are retrieved via
jam list jams,jam get console, andjam get networkin SKILL.md. - Boundary markers: No specific delimiters or safety instructions are defined to separate ingested data from agent instructions.
- Capability inventory: The agent has the capability to execute shell commands via the
jamCLI as seen in SKILL.md. - Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the recordings before processing.
Audit Metadata