plan-to-markdown

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of Markdown documentation and templates. No executable code (Python, JavaScript, etc.), shell scripts, or binaries were found in the skill or its referenced files.
  • [SAFE]: There are no network operations, such as curl or wget, and no external dependencies are downloaded or executed.
  • [NO_CODE]: As a no-code skill, it does not possess any logic that could be exploited for privilege escalation or persistence.
  • [PROMPT_INJECTION]: The skill processes untrusted user-provided plans.
  • Ingestion points: User-provided text plans are ingested via the agent's context in SKILL.md.
  • Boundary markers: No explicit boundary markers or instructions to disregard instructions within the plan are provided.
  • Capability inventory: The skill has no capabilities for network access, file writing, or command execution across SKILL.md and its references.
  • Sanitization: No sanitization of the input text is performed.
  • Conclusion: While the skill has an ingestion surface, the lack of any actionable capabilities prevents exploitation of indirect prompt injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 04:31 PM
Security Audit — agent-trust-hub — plan-to-markdown