The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions allow for user-specified parameters (such as time range or author name) to be directly interpolated into shell commands for git log. If the agent does not properly sanitize these inputs, it could lead to command injection, allowing arbitrary shell commands to be executed on the user's local system.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8). It ingests untrusted data from git log outputs and user-provided notes. Malicious instructions embedded in commit messages or work records could potentially manipulate the agent's output or influence its subsequent actions, such as writing to unauthorized file paths.
Ingestion points: User-provided notes and git log output in SKILL.md.
Boundary markers: None. The skill does not instruct the agent to use delimiters or ignore embedded instructions within the ingested data.
Capability inventory: Uses git log and git config via shell, and has the capability to write output to user-specified file paths.
Sanitization: Absent. There are no instructions for escaping or validating external content before processing.
[DATA_EXFILTRATION]: The skill accesses local configuration (git config user.name) and repository history (git log). While these are necessary for its primary purpose, they involve accessing potentially sensitive metadata about projects and contributors.

work-report-writer