source-comparison
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists only of a markdown description and frontmatter. No executable scripts (Python, JavaScript, Shell) or binaries are included in the skill package.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and compare external sources, creating a potential surface for indirect instructions to enter the agent's context.
- Ingestion points: External sources, papers, tools, frameworks, or claims mentioned in SKILL.md.
- Boundary markers: No delimiters or specific 'ignore instructions' warnings are defined in the skill text.
- Capability inventory: The skill implies the ability to write comparison matrices to the
outputs/directory. - Sanitization: No explicit sanitization or filtering of external content is described.
Audit Metadata