magicstarfishboost-seo-content-marketing-skill-suite

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it instructs the agent to ingest and analyze data from untrusted external websites provided by the user.
  • Ingestion points: Commands such as /content-audit <url> and /technical-seo <url> in SKILL.md ingest content from arbitrary external URLs.
  • Boundary markers: The prompt instructions do not include boundary markers or delimiters to help the agent differentiate between the skill's instructions and the external content being analyzed.
  • Capability inventory: The skill allows the agent to perform network requests (via API mentions) and implies file system access for logging and configuration.
  • Sanitization: There is no evidence of sanitization or validation protocols for the content retrieved from external sources.
  • [NO_CODE]: The provided skill consists entirely of a markdown instruction file (SKILL.md) and does not include any executable scripts, binaries, or compiled dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 03:17 AM
Security Audit — agent-trust-hub — magicstarfishboost-seo-content-marketing-skill-suite