logs
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill allows the agent to ingest output from containerized services via 'journalctl' and container engine logs. This content is untrusted and may contain malicious instructions designed to trigger unintended agent actions (indirect prompt injection).
- Ingestion points: Reading service logs via the 'charly logs' command (SKILL.md).
- Boundary markers: No explicit instruction delimiters are provided to prevent the agent from obeying instructions found within the logs.
- Capability inventory: The skill executes shell-level logging commands and is part of a suite ('/charly-core') that manages service lifecycles (SKILL.md).
- Sanitization: No sanitization or filtering of log data is described.
- [EXTERNAL_DOWNLOADS]: The documentation includes cross-references to image pulling workflows that utilize GitHub. These references to well-known service providers are documented for transparency and do not represent a security risk.
Audit Metadata