The Agent Skills Directory

[SAFE]: The skill contains only natural language instructions and no executable code, scripts, or system-level commands.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process log snippets, which are untrusted external inputs. While these inputs could theoretically contain prompt injection attempts, the skill does not define any tool-based capabilities (such as network operations, file writing, or command execution) that an attacker could exploit to harm the system. The risk is limited to the quality of the summarization output.
[NO_CODE]: The skill consists entirely of markdown instructions without any associated scripts, package manifests, or dynamic execution patterns.

log-summarizer