plan-to-tickets

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes external planning documents provided by the operator to generate tasks. If these documents contain instructions designed to manipulate the agent's behavior, they could be executed during the processing phase.
  • Ingestion points: Ingests source documentation (markdown/text files) in Step 1 of SKILL.md.
  • Boundary markers: Absent. The skill does not instruct the agent to use delimiters or specific ignore-tags when reading the source document.
  • Capability inventory: Includes MCP tools for creating, updating, and deleting resources in various project management trackers (ClickUp, Linear, etc.), as well as filesystem Write and Edit capabilities.
  • Sanitization: No explicit sanitization or validation of the input document content is described.
  • [COMMAND_EXECUTION]: The skill uses local shell commands to manage state and resolve task IDs.
  • Evidence: Steps 4 and 6 in SKILL.md use bash, echo, and awk to create and process CSV files (e.g., .plan-import/ids.csv) for mapping plan items to their external tracker counterparts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 08:14 AM
Security Audit — agent-trust-hub — plan-to-tickets