The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external 'Handover' records, including artifacts, revision summaries, and annotations. This creates a surface where instructions embedded within these external sources could potentially influence the agent's behavior.
Ingestion points: Data enters the context via handover.search, handover.show, and handover.pull commands as described in SKILL.md.
Boundary markers: The instructions do not specify the use of clear delimiters or instructions to ignore embedded prompts within the retrieved artifacts.
Capability inventory: The skill possesses the capability to execute shell commands (via the handover CLI), read and write files (handover pull ... --out <directory>), and publish new revisions to the network.
Sanitization: No explicit sanitization or validation of the external content is described prior to context integration.
[EXTERNAL_DOWNLOADS]: The skill directs users to https://handover.sh/install for installation and interacts with the handover.sh service for data synchronization. These resources are verified vendor assets for the author '44-pixels'.

handover-resume