analyzing-experiment-session-replays
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill uses established PostHog tools (
experiment-get,query-session-recordings-list, andexecute-sql) and HogQL queries to retrieve experiment metadata and session recordings. These operations are within the scope of legitimate data analysis for the PostHog platform. - [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from experiment results and recording metadata, creating an ingestion surface.
- Ingestion points: Data is ingested through the outputs of the
experiment-get,execute-sql, andquery-session-recordings-listtools (SKILL.md). - Boundary markers: No specific delimiters or boundary markers are defined in the workflow instructions for handling retrieved data.
- Capability inventory: The skill's capabilities are limited to data retrieval and qualitative analysis; it does not perform file-system writes, external network requests, or arbitrary shell command execution.
- Sanitization: The instructions do not specify any sanitization or filtering of the retrieved data before it is processed by the agent.
Audit Metadata