competitor-intelligence
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes untrusted data from X/Twitter, which could potentially contain adversarial instructions designed to influence or override the agent's behavior during analysis.
- Ingestion points: External data enters the agent context through tools like
x_get_tweets(post content),x_get_followers(user bios), andx_search_tweets(mentions and replies) as described inSKILL.md. - Boundary markers: The output templates and workflow instructions do not define explicit delimiters or instructions to ignore embedded commands within the fetched social media data.
- Capability inventory: The skill leverages MCP tools for data retrieval and references local JavaScript scripts (e.g.,
src/competitorAnalysis.js) for data processing and comparison. - Sanitization: No sanitization, filtering, or validation mechanisms for the retrieved external content are mentioned in the skill definition.
Audit Metadata