launch-day-conductor
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access commands were found in the skill file.
- [PROMPT_INJECTION]: Analysis of the attack surface for indirect prompt injection (Category 8) shows that while the skill ingests untrusted data from community threads and telemetry exports, it explicitly instructs the agent to treat this data as untrusted and ignore any embedded commands, effectively mitigating the risk.
- [EXTERNAL_DOWNLOADS]: The skill references connector scripts (e.g.,
scripts/connectors/hn.py,scripts/connectors/gdelt.py) for accessing public telemetry. These are internal vendor resources used for fetching data from well-known public services and do not represent a remote code execution risk.
Audit Metadata