share-of-voice
Warn
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends the use of an external tool,
TweetClaw(@xquik/tweetclawon npm), which originates from an unverified source (github.com/Xquik-dev/tweetclaw). - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting and processing data from external, untrusted sources such as social media mentions.
- Ingestion points: The skill collects social media post excerpts, competitor profile data, and AI engine citation metrics (referenced in
x-twitter-source-evidence.mdand GEO audits). - Boundary markers: No specific delimiters or instructions are used to separate untrusted social media content from the agent's internal logic.
- Capability inventory: The skill has the ability to execute shell commands (running
competitor-tracker.py) and perform file operations within the~/.claude-marketing/directory. - Sanitization: The instructions lack explicit requirements for sanitizing or escaping the text excerpts collected from external platforms before analysis.
- [COMMAND_EXECUTION]: The skill uses shell commands to invoke a local Python script (
competitor-tracker.py) for data persistence and trend tracking.
Audit Metadata