internal-linking-optimizer

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection through the processing of untrusted external content.
  • Ingestion points: The skill ingests data from external URLs or sitemaps provided by the user as part of its core SEO analysis functionality (documented in SKILL.md).
  • Boundary markers: There are no explicit instructions or delimiters defined to guide the agent in ignoring potential malicious instructions embedded within the scraped external content.
  • Capability inventory: The skill is directed to write analysis results and dated summaries to the local memory/ directory for persistence (documented in SKILL.md).
  • Sanitization: The instruction set does not specify any validation, escaping, or sanitization processes for the content retrieved from external sources before it is interpreted or stored in memory files.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 07:25 PM