plan-ledger-tasks-yylo

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is configured with enable-shell-directives: true, allowing it to execute shell commands. It specifically instructs the agent to invoke a local project script located at .juno_task/scripts/kanban.sh to create and manage tasks.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection as it is designed to ingest and process untrusted external data, including project instructions and product code from a worktree.
  • Ingestion points: The skill reads project instructions and product code (SKILL.md, step 1).
  • Boundary markers: There are no explicit delimiters or instructions to ignore potential injections within the ingested project data.
  • Capability inventory: The skill can execute shell scripts and perform metadata operations (SKILL.md, steps 4 and 5).
  • Sanitization: No evidence of sanitization or validation of the ingested content is present.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 11:12 PM
Security Audit — agent-trust-hub — plan-ledger-tasks-yylo