The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local environment to generate reports.
Ingestion points: In SKILL.md (Step 1) and agents/openai.yaml (Step 1), the agent is instructed to review git log output and modified files from the past 24 hours.
Boundary markers: The instructions do not specify delimiters or techniques to isolate git commit messages from the system prompt.
Capability inventory: The skill utilizes bash, view_file, write_to_file, and replace_file_content as declared in the SKILL.md frontmatter.
Sanitization: No explicit filtering or sanitization of git logs is performed before processing by the model.
[EXTERNAL_DOWNLOADS]: The README.md file contains installation instructions using npx skills add harshsinghmp/muse-skills. This refers to the skill author's own repository and is a standard distribution mechanism.
[COMMAND_EXECUTION]: The skill uses bash to execute git log --since="24 hours ago" in SKILL.md. This is a read-only operation restricted to the local repository metadata to fulfill the skill's primary purpose of summarizing daily activity.

daily-standup-coach