counter-narrative

Warn

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill accesses sensitive marketing configuration and brand profiles stored in ~/.claude-marketing/. This represents a data exposure risk as it reads files from the user's home directory.
  • [COMMAND_EXECUTION]: The skill executes a local Python script narrative-mapper.py to generate counter-narrative strategies based on brand context.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through competitor evidence URLs and artifacts. Malicious instructions hosted on a competitor's site could influence the agent's behavior while it has access to local brand data. 1. Ingestion points: Competitor evidence URLs and provided artifacts (SKILL.md). 2. Boundary markers: No delimiters or ignore instructions are used for external content. 3. Capability inventory: Access to local filesystem (~/.claude-marketing/) and execution of local Python scripts (narrative-mapper.py). 4. Sanitization: No sanitization or validation of the remote content is specified.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 1, 2026, 01:18 AM