auditing-experiments-flags
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from PostHog API responses (experiment definitions, flag configurations, and activity logs) which may contain attacker-controlled content (such as experiment descriptions or variant names) that could be used to inject malicious instructions into the agent's context.
- Ingestion points: Data is fetched through multiple tools including
experiment-get,experiment-list,feature-flag-get-definition,feature-flag-get-all, andfeature-flags-activity-retrieveas described inSKILL.md. - Boundary markers: The instructions lack explicit boundary markers or instructions for the agent to ignore potentially malicious embedded content within the fetched metadata.
- Capability inventory: The skill has the capability to generate markdown reports for the user and create project notebooks as outlined in
SKILL.md. - Sanitization: The skill does not define any sanitization, filtering, or validation logic for the external content before it is interpolated into reports or used to drive logic in
synthesis-patterns.md.
Audit Metadata