tech-blogger-writer
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external files (
content-outline.md,research-findings.json) which could contain malicious instructions. - Ingestion points: The skill instructions in
SKILL.mdreference reading specific outline and research files. - Boundary markers: There are no instructions to the agent to distinguish between its primary instructions and the data found in input files.
- Capability inventory: No specific tools or scripts are defined in the skill package, though it would use platform-default capabilities for file reading and text generation.
- Sanitization: No input validation or content filtering mechanisms are present.
Audit Metadata