posthog
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using
npx @useclawlink/clito manage authentication, list actions, and perform data operations in PostHog. - [EXTERNAL_DOWNLOADS]: The skill triggers the download and execution of the
@useclawlink/clipackage from the public NPM registry at runtime via thenpxcommand. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill ingests data from external PostHog environments, including project members, event definitions, funnel insights, and experiment statistics (documented in
SKILL.md). - Boundary markers: There are no explicit instructions for the agent to use boundary markers or to ignore instructions that might be embedded in the retrieved analytics data.
- Capability inventory: The skill grants the agent the ability to write back to PostHog using the
npx @useclawlink/cli runcommand. - Sanitization: The skill does not define specific sanitization or validation steps for data retrieved from the PostHog API before it is processed by the agent.
Audit Metadata