competitive-intel
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists solely of Markdown documentation, templates, and frameworks. It does not include any scripts, binaries, or executable code, posing no direct risk of malicious execution.\n- [INDIRECT_PROMPT_INJECTION]: The intelligence workflows described in the skill involve the ingestion of untrusted external data, such as competitor websites, public review platforms, and social media content. While the skill does not provide the automation scripts to fetch this data, an agent performing these tasks would be susceptible to malicious instructions embedded in those external sources.\n
- Ingestion points: External competitor websites, public review sites (G2, Capterra), and social media platforms (LinkedIn, Twitter) mentioned as sources in
references/ci-playbook.md.\n - Boundary markers: None explicitly defined in the provided templates for handling retrieved text.\n
- Capability inventory: No executable tools or scripts are provided within this skill package.\n
- Sanitization: No input sanitization or filtering logic is provided in the skill documentation.
Audit Metadata