logs-tool
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions utilize
bun logs-toolto execute commands that interact with the local file system and remote pod environments. - [INDIRECT_PROMPT_INJECTION]: This skill presents an attack surface for indirect prompt injection because application logs often ingest and record unvalidated data from external users (e.g., HTTP headers, error messages). An attacker could craft specific log entries to influence the agent's behavior when it reads those logs.
- Ingestion points: Log content is ingested into the agent context via the
readcommands defined inSKILL.md. - Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore potentially malicious content within the logs.
- Capability inventory: The skill has the capability to execute shell commands (
bun logs-tool) and read files. - Sanitization: There is no evidence of sanitization or filtering of the log output before it is processed by the agent.
Audit Metadata