The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes a local Python script scripts/launch_readiness_scorer.py to calculate readiness scores based on a JSON checklist. This is a controlled execution of a script bundled with the skill.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from external files, which introduces a potential surface for indirect prompt injection.
Ingestion points: The agent is instructed in SKILL.md to read .claude/product-marketing-context.md if available. Additionally, the readiness scorer script reads external JSON files via the --checklist argument.
Boundary markers: The instructions do not define specific delimiters or security warnings to treat the content of these external files as untrusted data.
Capability inventory: The skill has the capability to read local files and execute a bundled Python script.
Sanitization: There is no evidence of explicit sanitization or filtering of the content ingested from the marketing context or JSON checklist before it is incorporated into the agent's reasoning process.

launch-strategy