competitive-ads-extractor
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow that involves scraping external data from Facebook and LinkedIn Ad Libraries. This creates an ingestion surface where untrusted content from third-party websites is processed by the agent, potentially exposing it to hidden instructions within ad copy.
- Ingestion points: Data extraction from Facebook Ad Library and LinkedIn Ads as described in the 'What This Skill Does' section of
SKILL.md. - Boundary markers: The instructions do not specify any delimiters or warnings to ensure the agent ignores instructions that may be embedded in the scraped text.
- Capability inventory: The workflow implies network access for scraping and file system operations for saving screenshots and analysis reports to
~/competitor-ads/. - Sanitization: The skill documentation does not mention any sanitization or validation of the content retrieved from external sources.
- [NO_CODE]: The skill consists entirely of documentation, usage examples, and license information. It does not provide any executable scripts (.py, .js) or automated configuration files, requiring the agent to rely on its existing toolset to fulfill the described tasks.
Audit Metadata