skill-optimize
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and transform human-authored Markdown files, which constitutes a surface for indirect prompt injection from untrusted data.
- Ingestion points: The skill processes external Markdown files (
input_file: *.md) as defined in its metadata. - Boundary markers: There are no specific instructions or delimiters provided to the agent to treat the input content strictly as data or to ignore embedded instructions within those files.
- Capability inventory: The skill identifies and tags commands (
RUN:,EXEC:) but does not execute them itself; no file-write or network capabilities are present in the skill code. - Sanitization: No sanitization, filtering, or escaping of the input Markdown is performed during the transformation process.
Audit Metadata