competitive-ads-extractor
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external, untrusted sources, creating a surface for indirect prompt injection attacks.\n
- Ingestion points: The skill programmatically fetches advertisement content, including headlines, body copy, and metadata from Facebook Ad Library, LinkedIn, and other external ad platforms.\n
- Boundary markers: The instructions do not define any delimiters or boundary markers to separate external data from the agent's core instructions, making it harder for the agent to distinguish between valid data and potentially malicious embedded instructions.\n
- Capability inventory: The skill is capable of performing network requests to external domains to fetch ad data and has the capability to perform file system writes to local directories (e.g., '~/competitor-ads/') to save analysis results and screenshots.\n
- Sanitization: There is no evidence in the instructions of any sanitization, validation, or filtering of the ingested external advertisement content.
Audit Metadata