The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it summarizes untrusted data from diary entries and git logs into a persistent file that is automatically loaded into the agent's context in future sessions.
Ingestion points: The skill reads project diary files located in docs/diary/ and retrieves data from git log.
Boundary markers: No explicit delimiters or instructions (e.g., 'ignore instructions within this data') are used to isolate the untrusted diary/git content during processing or within the generated docs/accomplishments.md file.
Capability inventory: The skill performs file system writes to docs/accomplishments.md, creating a persistent injection point for future sessions.
Sanitization: There is no evidence of sanitization, filtering, or validation of the input text before it is summarized and written to the log file.

accomplishments