competitive-ads-extractor
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to scrape and analyze content from external, untrusted sources such as the Facebook Ad Library and LinkedIn. This creates a surface for indirect prompt injection attacks where malicious instructions could be embedded in competitor ad copy.
- Ingestion points: Ad headlines, body copy, and metadata retrieved from external websites are processed by the agent.
- Boundary markers: The instructions lack specific delimiters or guardrails to prevent the agent from executing instructions potentially hidden within the scraped ad text.
- Capability inventory: The skill records that it saves screenshots and analysis reports to the local file system (e.g.,
~/competitor-ads/) and uses web browsing tools to access external URLs. - Sanitization: No explicit sanitization or filtering mechanisms are defined for the data extracted from the external platforms.
- [NO_CODE]: The skill consists entirely of natural language instructions and examples; it does not contain any executable scripts, binaries, or configuration files that would introduce traditional code-based vulnerabilities.
Audit Metadata