effective-big-pics-little-words
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and configuration metadata. There are no scripts, binaries, or command-line instructions provided within the package.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for transforming external data (the subject being discussed) into HTML output. While this creates a surface for processing untrusted data, the risk is negligible as the skill lacks capabilities to perform sensitive operations.
- Ingestion points: The conversation subject or user input (SKILL.md).
- Boundary markers: None present.
- Capability inventory: None; the skill frontmatter sets
disable-model-invocation: trueand defines noallowed-tools. - Sanitization: None specified.
- [EXTERNAL_DOWNLOADS]: The
MIRROR.mdfile references a GitHub repository (github.com/plannotator/effective-html.git) as the source of the mirrored skill content. This is an informational reference and does not involve automated downloads or runtime execution.
Audit Metadata