The Agent Skills Directory

[COMMAND_EXECUTION]: The skill is designed to execute a local script scripts/create_delegation.py to generate task packages. This is a functional requirement of the skill using a locally provided resource.
[PROMPT_INJECTION]: The skill processes external, potentially untrusted data from project files which creates a surface for indirect prompt injection attacks.
Ingestion points: Reads task descriptions and metadata from .pm/backlog/items.yaml, .pm/config.yaml, and .pm/roadmap.md.
Boundary markers: The skill does not define explicit boundary markers or instructions to ignore embedded commands within the ingested project data.
Capability inventory: The skill has the capability to execute command-line scripts (scripts/create_delegation.py).
Sanitization: There is no evidence of sanitization or filtering of content retrieved from the project files before it is included in delegation packages.

work-delegator