The Agent Skills Directory

[SAFE]: The skill provides legitimate marketing tools designed for content scaffolding, profile auditing, and growth tracking. Technical review of the five included Python scripts shows they rely solely on the Python standard library and perform only local string manipulation, regex-based auditing, and basic file logging within the skill's own directory.
[INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection by processing external content such as user-provided bios and competitor profile data.
Ingestion points: Untrusted data enters the skill context through the --bio argument in scripts/profile_auditor.py and the --import functionality in scripts/competitor_analyzer.py.
Boundary markers: The scripts do not implement specific delimiters or 'ignore' instructions for the ingested text.
Capability inventory: The skill's capabilities are restricted to terminal output and local file writes to a .growth-data directory managed by scripts/growth_tracker.py.
Sanitization: Data is processed using standard regular expressions for pattern matching; however, the skill does not use the data in a way that triggers dangerous operations like network requests or command execution.

x-twitter-growth