optimize-md
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and processes external markdown files provided via the
$ARGUMENTSpath, which introduces a risk of indirect prompt injection if the target file contains malicious instructions designed to subvert the agent's behavior. - Ingestion points: The skill reads content from a file path provided as an argument, as described in the workflow of
SKILL.md. - Boundary markers: There are no boundary markers or instructions to treat the file content as untrusted data, increasing the likelihood that the agent might follow instructions embedded within the document during the analysis phase.
- Capability inventory: The skill possesses the capability to read from and write (overwrite) local files, which could be abused to modify or expose sensitive data if an injection occurs.
- Sanitization: No sanitization, escaping, or validation of the input file's content is performed before the agent analyzes and rewrites it.
Audit Metadata