linkedin-abm-monthly-report
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
weasyprintcommand-line utility to convert generated HTML reports into PDF documents for user delivery. - [EXTERNAL_DOWNLOADS]: The skill references branded templates and report assets located in the official
ZENABM/linkedin-abm-skillsrepository on GitHub. - [PROMPT_INJECTION]: The skill processes untrusted data from external sources, presenting an indirect prompt injection surface.
- Ingestion points: Data is retrieved from LinkedIn Ads via
get_linkedin_metricsandget_creative_performance, as well as CRM deal information from HubSpot. - Boundary markers: The instructions do not define explicit delimiters or warnings to ignore instructions embedded within the ingested campaign names or company data.
- Capability inventory: The skill has the capability to execute shell commands (
weasyprint) and perform file system operations (writing HTML and PDF files). - Sanitization: No specific sanitization or escaping protocols are mentioned for data interpolated into the HTML report structure.
Audit Metadata