serp-tracker

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data from search results, creating a potential surface for indirect prompt injection attacks.\n
  • Ingestion points: The skill retrieves and processes snippets, 'People Also Ask' questions, and 'AI Overview' summaries via Moz and Google Search Console MCPs in Process step 2.\n
  • Boundary markers: There are no explicit delimiters or boundary markers specified to separate the external search content from the agent's core instructions.\n
  • Capability inventory: The skill has permission to read and write to local marketing data directories (~/.claude-marketing/) as described in Process steps 1 and 3.\n
  • Sanitization: No sanitization of the retrieved external SERP content is mentioned before it is processed by the seo-specialist agent.\n- [DATA_EXPOSURE]: The skill accesses local application-specific files that contain brand profile and keyword information.\n
  • Access points: Reads brand configuration data (profile.json) and keyword lists (keywords.json) from directories under ~/.claude-marketing/brands/.\n
  • Context: While this access is necessary for the skill's stated purpose, it involves reading sensitive business-related files from the local filesystem.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 12:41 AM
Security Audit — agent-trust-hub — serp-tracker