light-research
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill package contains only Markdown instructions and YAML configuration files. There are no executable scripts, binaries, or third-party dependencies provided within the skill.\n- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and process data from external primary sources such as official documentation and source code. This creates a surface for indirect prompt injection if an attacker controls those external sources.\n
- Ingestion points: External official documentation, source code repositories, and API specifications.\n
- Boundary markers: No specific delimiters or "ignore" instructions are provided to separate external content from the agent's internal logic.\n
- Capability inventory: The skill allows the agent to write findings into Markdown files within the user's repository.\n
- Sanitization: No sanitization or validation logic is defined for the content retrieved from external sources.
Audit Metadata