The Agent Skills Directory

[SAFE]: The skill consists exclusively of instructional Markdown content. No malicious patterns, obfuscation, hardcoded credentials, or unauthorized command executions were detected. The skill instructions align with its stated purpose of improving professional reporting.\n- [NO_CODE]: No executable scripts, binaries, or configuration files are included in this skill. It relies entirely on the agent's natural language processing capabilities.\n- [INDIRECT_PROMPT_INJECTION]: The skill instructions (SKILL.md) suggest ingesting external data such as git history, chat highlights, and task management records. Ingestion points: External logs and messaging platforms. Boundary markers: None provided in the template. Capability inventory: Limited to text generation; no network operations, file writing, or subprocess execution capabilities are requested by the skill. Sanitization: No input validation or instruction filtering is implemented. Due to the lack of dangerous capabilities, the risk of an indirect prompt injection attack through processed logs is considered negligible for this skill.

weekly-report