jam
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: Employs
bash -cto wrapcurlcommands, ensuring that environment variables like$JAM_TOKENare preserved during execution. This is a documented functional requirement for the skill to operate correctly. - [EXTERNAL_DOWNLOADS]: Connects to
https://mcp.jam.dev/mcpto perform API calls. This domain belongs to the official Jam.dev service, which is the intended target for this skill. - [PROMPT_INJECTION]: Indirect prompt injection surface identified.
- Ingestion points: Data from bug reports (logs, events, transcripts) is retrieved via
getConsoleLogs,getNetworkRequests, and other tools inSKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded content are present in the provided examples.
- Capability inventory: The skill has network access (
curl) and local command execution capabilities (bash -c) as seen inSKILL.md. - Sanitization: No specific sanitization or escaping of the retrieved data is mentioned.
Audit Metadata