content-research-writer
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external information gathered during the research phase, which creates a potential surface for indirect prompt injection if the retrieved content contains malicious instructions.
- Ingestion points: External data retrieved from the web during research tasks described in SKILL.md (Section 3).
- Boundary markers: The instructions do not specify explicit delimiters or "ignore previous instructions" guards for the research data.
- Capability inventory: The agent relies on implied search tools and file manipulation (reading/writing drafts) to perform its tasks.
- Sanitization: The instructions do not mention filtering or sanitizing external content before it is included in the writing process.
- [NO_CODE]: The skill consists entirely of instructional Markdown and YAML frontmatter. It does not include any scripts (.py, .js, .sh), binaries, or configuration files that execute code on the host system.
Audit Metadata