skills/iqrow/skills/teardown-apply/Gen Agent Trust Hub

teardown-apply

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to execute a local Node.js script (map.mjs) with several arguments derived from user input or external links (e.g., <slug>, <id>, <parent>). This pattern creates a potential command injection surface if the agent does not properly sanitize shell metacharacters within these variables before invoking the command line.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the user's project (code, drafts, notes) and external teardown maps which can be loaded from arbitrary URLs. This content could contain instructions designed to manipulate the agent's output or logic during the analysis phase.
  • Ingestion points: Project files (code, drafts, design docs, notes) and teardown maps (JSON files or URLs) referenced in SKILL.md steps 1 and 2.
  • Boundary markers: Absent; the instructions do not specify any delimiters or safety warnings to ignore instructions embedded within the analyzed data.
  • Capability inventory: The skill possesses the ability to execute shell commands (node), read arbitrary files in the project directory, and write to documentation files.
  • Sanitization: Absent; there is no mention of validation, filtering, or escaping for the data ingested from the project or external maps.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 02:43 PM