research
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates the ingestion of data from external primary sources like documentation and source code to generate research files, which introduces a risk of indirect prompt injection.
- Ingestion points: The agent is instructed to investigate questions against external primary sources (docs, source code, specs) as described in SKILL.md.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the source data are provided.
- Capability inventory: The agent has the capability to write research findings into a Markdown file within the repository (SKILL.md).
- Sanitization: There is no specified requirement for sanitizing, validating, or filtering the content retrieved from external sources.
Audit Metadata