prompt-export
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): The skill is designed to ingest untrusted user artifacts (sketches, docs, bullet points) and transform them into a
prompts.mdfile intended for execution by another agent (Claude Code). This creates an attack surface where malicious instructions embedded in the artifacts could influence the generated prompts. - Ingestion points:
SKILL.mdStep 1 ("Gather Artifacts") accepts user-provided artifacts in various formats. - Boundary markers: Absent. The skill does not provide instructions to use delimiters or warnings to ignore instructions inside the ingested content.
- Capability inventory: The skill uses the
Writetool to automatically save output toprompts.mdin the project root. - Sanitization: Absent. No filtering, validation, or escaping of the user-provided data is performed before it is transformed into prompts.
- No Code (SAFE): The skill contains no executable scripts, binaries, or configuration files that could execute system commands. It consists entirely of markdown instructions and guidelines.
Audit Metadata