The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local script named gsd-tools.cjs with subcommands such as init and roadmap analyze to manage and analyze the project roadmap.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it processes untrusted data from multiple sources to determine its autonomous actions.
Ingestion points: Data is ingested from ROADMAP.md, STATE.md, and the user-provided {{GSD_ARGS}} variable.
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands were found in the skill's logic.
Capability inventory: The skill has the capability to execute local scripts via gsd-tools.cjs and spawn new agents with specific prompts using spawn_agent.
Sanitization: There is no evidence of sanitization or validation of the input data before it is used to influence the workflow or the prompts passed to spawned agents.

gsd-autonomous