competitive-positioning
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external websites via WebFetch and includes this data in a generated HTML file.
- Ingestion points: Phase 2, Step 2 in SKILL.md fetches content from competitor URLs provided by the user or found through search.
- Boundary markers: There are no explicit instructions to sanitize or escape the scraped content before embedding it into the HTML report.
- Capability inventory: The skill utilizes WebFetch for external data retrieval and writes the resulting analysis into a local HTML file.
- Sanitization: The lack of content sanitization poses a potential risk of Cross-Site Scripting (XSS) if malicious payloads are present on the scraped websites and rendered in the user's browser.
- [DYNAMIC_EXECUTION]: The skill generates a local HTML file that contains an embedded JavaScript block for navigation. While this uses a static template from the skill instructions, the generation of executable content from a process that also handles external data contributes to the attack surface.
Audit Metadata