skills/vm0-ai/vm0-skills/jam/Gen Agent Trust Hub

jam

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses common system tools such as curl, jq, grep, awk, and tr to manage API sessions and process JSON responses.
  • [DATA_EXFILTRATION]: Communicates with the official domains jam.dev and mcp.jam.dev to exchange bug reporting data. All network operations are directed to the platform's legitimate API.
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from external sources, presenting a surface for indirect prompt injection.
  • Ingestion points: Retrieves console logs, network request details, user events, and video transcripts from bug reports (SKILL.md).
  • Boundary markers: No explicit delimiters are present to isolate the ingested content from the agent's instructions.
  • Capability inventory: Executes shell commands, performs network requests via curl, and writes to temporary files (SKILL.md).
  • Sanitization: No input sanitization or validation is applied to the ingested data before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 04:44 PM
Security Audit — agent-trust-hub — jam