The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified during the analysis of the skill's instructions, reference documentation, or supporting scripts.
[REMOTE_CODE_EXECUTION]: The skill includes a Python script (scripts/launch_readiness_scorer.py) which is well-documented and uses only the Python standard library. It does not perform network operations, download external content, or execute arbitrary commands.
[DATA_EXPOSURE]: The instructions direct the agent to read project-specific marketing context from a local file (.claude/product-marketing-context.md). This is a common and safe pattern for maintaining context within the agent's environment and does not involve unauthorized data access or exfiltration.
[PROMPT_INJECTION]: The skill instructions are focused on providing expert marketing advice and do not contain any attempts to bypass safety filters or override system-level instructions.
[INDIRECT_PROMPT_INJECTION]: While the skill processes external data (checklist files and context documents), it lacks the capabilities (such as file-writing or network access) that would make it vulnerable to exploitation via indirect injection.

launch-strategy