seo-memory

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting untrusted user data and storing it in a project file that may be referenced by other skills.
  • Ingestion points: User-provided business facts and project context are ingested via the main agent and subagent (SKILL.md, references/update-guide.md).
  • Boundary markers: Absent. The skill does not instruct the agent to use delimiters or ignore instructions embedded within the provided project facts.
  • Capability inventory: The skill performs file read and write operations on ./seo-memory.md (SKILL.md, references/update-guide.md).
  • Sanitization: Absent. While the skill filters for 'implementation details', it lacks security-focused sanitization to prevent the storage of malicious instructions within the project memory.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 08:15 AM