runtime-observer
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes untrusted telemetry data from an external collector.
- Ingestion points: Data enters the agent context via network GET requests in
scripts/observer.pyandscripts/observer_client.pywhen fetching logs, traces, and exception details. - Boundary markers: There are no explicit instructions or delimiters in the documentation to warn the agent about ignoring potential instructions embedded within the retrieved telemetry data.
- Capability inventory: The skill allows the agent to make subsequent network requests to the collector API based on the data it reads.
- Sanitization: The provided scripts do not perform local sanitization or filtering of the retrieved telemetry content before presenting it to the agent.
Audit Metadata