seo-research
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it reads context from local markdown files (
docs/seo/brand-voice.mdanddocs/seo/topical-clusters.md) and incorporates that data directly into a generated prompt for another session. - Ingestion points: Reads local configuration files from the project directory (SKILL.md).
- Boundary markers: Absent. No delimiters or instructions are used to separate ingested content from the system instructions.
- Capability inventory: Includes the ability to write files to the local filesystem (SKILL.md).
- Sanitization: Absent. Content is extracted and used to populate prompt sections without validation or escaping.
- [COMMAND_EXECUTION]: The skill uses a file-writing tool to save generated content to the local filesystem. While it supports user-provided paths for output, this is a standard operational feature for managing project documentation and does not exhibit malicious intent (SKILL.md).
Audit Metadata