The Agent Skills Directory

[SAFE]: The skill uses dynamic context injection (!git log) to fetch the last two weeks of commit history. This is a legitimate use of the feature for development-oriented tasks and does not involve exfiltration, sensitive file access, or command injection from user-supplied arguments.
[SAFE]: The skill interacts with project-specific directories (production/sprints/, production/milestones/) to read plans and write retrospective reports. These operations are within the expected scope of the tool's functionality.
[PROMPT_INJECTION]: Indirect prompt injection surface detected. The skill ingests untrusted data from git logs and codebase comments (TODO/FIXME) and possesses file-writing capabilities.
Ingestion points: Reads git commit messages via git log and codebase content via Grep/Read.
Boundary markers: Absent. The skill does not instruct the agent to ignore instructions embedded in the processed data.
Capability inventory: Includes Read, Glob, Grep, and Write tools.
Sanitization: Not specified; the agent processes raw data from the codebase and git history.

retrospective