smart-intel
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill generates a local HTML portal by interpolating user-provided inputs and external search results into a static template without proper HTML escaping, creating a potential cross-site scripting (XSS) surface within the generated file.
- Ingestion points: Data enters the agent context via the
--companyand--industrycommand-line arguments inscripts/gen_smart_intel.py, as well as results frompatsnap_searchandweb_searchtools. - Boundary markers: Absent; the data is directly concatenated into the HTML string buffer.
- Capability inventory: The skill includes the capability to write files to the local file system (
Path.write_textingen_smart_intel.py). - Sanitization: Absent; the Python script uses raw string concatenation to build the interactive UI, which does not filter or escape potentially malicious characters (e.g.,
<script>tags) that might be present in enterprise names or news headlines.
Audit Metadata