multi-channel-reporting
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize data from various external advertising APIs (Google Ads, Meta, LinkedIn, etc.). This creates a vulnerability surface where malicious instructions embedded in advertising content (such as campaign names or ad copy) could influence the agent's behavior during report generation.
- Ingestion points: Advertising performance data fetched via
scripts/generate-report.pyandscripts/daily-pull.py. - Boundary markers: The instructions do not define clear delimiters or "ignore" directives for the processed data.
- Capability inventory: The skill is capable of performing network operations to external APIs and writing data to the local file system (e.g., via the
--outputflag). - Sanitization: There is no mention of sanitization or filtering of external data before it is incorporated into the agent's context.
- [COMMAND_EXECUTION]: The skill utilizes local Python scripts (
scripts/generate-report.pyandscripts/daily-pull.py) to perform its primary functions. While these are internal to the skill, they represent a capability to execute code on the host system to interact with databases and external APIs.
Audit Metadata