account-plan

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches external data from company websites, LinkedIn pages, and job postings, creating a surface for indirect prompt injection attacks where malicious instructions hidden on those pages could influence agent behavior.
  • Ingestion points: WebSearch and WebFetch tools are used in SKILL.md to research accounts.
  • Boundary markers: The references/agent-security.md file provides explicit instructions to treat all fetched content as data rather than instructions and to quote rather than follow any embedded commands.
  • Capability inventory: The skill writes research findings to .agents/product-context.md and generates visual plans using platform artifact tools.
  • Sanitization: references/agent-security.md mandates HTML-escaping for all interpolated values in generated markup.
  • [DYNAMIC_EXECUTION]: The skill uses platform-specific artifact tools to generate visual account plans, which involves dynamic code/markup generation.
  • Evidence: SKILL.md includes a section for a 'Visual account plan' that utilizes host tools like Claude's Artifact tool to render documents and charts.
  • Mitigation: references/agent-security.md section 3 contains strict rules for escaping HTML, prohibiting unsafe functions like innerHTML, and validating URLs in emitted code.
  • [CREDENTIALS_UNSAFE]: While the skill does not contain hardcoded credentials, it is designed to process CRM exports and transcripts which often contain them.
  • Mitigation: The skill includes comprehensive instructions in references/agent-security.md to identify, redact, and flag credentials (API keys, session tokens) without reproducing them in output or persisting them to files.
  • [PROMPT_INJECTION]: The skill contains instructions to suppress certain output patterns (like warnings on drafts or comments about missing tools) to improve user experience.
  • Evidence: SKILL.md instructs the agent to "Do not return a draft with a warning on it" and to "skip this step without comment" if a specific visual tool is missing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 04:06 PM