The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes the plannotator review command in the shell. This is the primary functionality of the skill and is considered safe as it utilizes the author's own tool.
[PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection because it processes feedback from an external source.
Ingestion points: The agent ingests data from annotations and comments provided through the Plannotator UI as described in the process section of SKILL.md.
Boundary markers: There are no delimiters or instructions provided to the agent to help it distinguish between data and potentially malicious instructions within the feedback.
Capability inventory: The skill has the capability to execute shell commands via the plannotator utility.
Sanitization: There is no evidence of input validation or sanitization for the review comments before they are handled by the agent.

plannotator-review