competitor-monitoring
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown instructions and metadata. It does not include any scripts, configuration files, or executable binaries that could be used for malicious purposes.
- [INDIRECT_PROMPT_INJECTION]: The workflow involves scanning and analyzing content from external, untrusted sources such as competitor websites, blogs, and review platforms. This creates a theoretical surface for indirect prompt injection where external content could attempt to influence the agent's analysis.
- Ingestion points: The instructions specify scanning competitor pricing pages, changelogs, job postings, blog posts, social media, and review sites (G2, Capterra, etc.) as detailed in SKILL.md.
- Boundary markers: The workflow does not explicitly define the use of delimiters or instructions to the agent to ignore embedded commands within the fetched data.
- Capability inventory: No code execution or filesystem write capabilities are provided within the skill itself.
- Sanitization: The instructions do not mention specific sanitization or filtering protocols for the ingested content.
Audit Metadata