category-narrative-mapper
Pass
Audited by Gen Agent Trust Hub on Jul 5, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill involves ingesting data from external websites, search results, and web archives, which creates a potential surface for indirect prompt injection. The skill mitigates this by including explicit instructions for the agent to treat all scraped and external content as untrusted and to ignore any instructions embedded within that data.
- [COMMAND_EXECUTION]: The skill references the use of local connector scripts (
firecrawl.py,tavily.py,wayback.py) to perform its primary functions. These are standard research tools within the skill's operational context and do not represent unauthorized or malicious command execution. - [DATA_EXFILTRATION]: While the skill reads and writes data to the agent's memory, all operations are consistent with its stated purpose of marketing analysis. Data movement is confined to internal memory directories (
memory/research/,memory/narrative/,memory/claims/) and does not involve exfiltrating sensitive user information to external domains.
Audit Metadata