webinar-marketing
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a local Python script,
scripts/webinar_funnel_scorer.py, to perform diagnostic calculations on webinar funnel metrics. This script is self-contained, uses only standard libraries, and does not perform any network operations or sensitive file system modifications. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from untrusted sources, which creates a potential surface for indirect prompt injection.
- Ingestion points: The skill reads user-supplied marketing metrics from
funnel.jsonand fetches brand context from a local file.claude/product-marketing-context.md. - Boundary markers: There are no explicit instructions or delimiters used to warn the agent to ignore instructions that might be embedded within these data files.
- Capability inventory: The skill possesses the ability to execute local subprocesses (Python) and read files within the user's project environment.
- Sanitization: The skill relies on standard JSON parsing for data ingestion, which validates the structure but does not sanitize the content of strings against malicious natural language instructions.
Audit Metadata