The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, persistence mechanisms, or credential theft attempts were detected. The skill's behavior is consistent with its stated purpose of marketing analysis.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes content from untrusted external URLs. Ingestion points: Untrusted data enters the agent context through the site content fetched via the user-provided URL in SKILL.md. Boundary markers: Absent; there are no instructions to the agent to treat external content as untrusted or to ignore embedded instructions. Capability inventory: The skill writes analysis to FUNNEL-ANALYSIS.md but does not invoke subprocesses or execute dynamic code. Sanitization: Absent; the skill performs no validation or filtering of the fetched site content.

market-funnel