skills/jamdesk/skills/update-jamdesk/Gen Agent Trust Hub

update-jamdesk

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes the 'jamdesk' CLI utility with 'dev', 'validate', and 'broken-links' subcommands to verify documentation integrity. These are vendor-owned tools associated with the jamdesk documentation platform.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface in Phase 3 by reading and analyzing documentation content.\n
  • Ingestion points: Documentation files found in the directory path defined by '.jamdesk-docs-path'.\n
  • Boundary markers: None identified. The agent processes file content without delimiters or explicit instructions to ignore embedded commands.\n
  • Capability inventory: Ability to write files, perform git commits and pushes, and execute vendor CLI commands.\n
  • Sanitization: None identified. No sanitization or filtering of the documentation content is performed before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 09:58 PM