competitor-analysis
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and analyze external advertising content from the Facebook Ads Library (messaging, offers, and creative copy). This data is untrusted and could contain malicious instructions designed to manipulate the agent's summary or behavior. • Ingestion points: The get_meta_ads tool retrieves external data into the agent's context. • Boundary markers: There are no explicit delimiters or instructions provided to separate the untrusted ad content from the agent's core instructions. • Capability inventory: Results are processed using a Python script (scripts/analyze-competitor.py). • Sanitization: No sanitization or filtering of the retrieved external content is documented.
- [COMMAND_EXECUTION]: The skill instructions specify the execution of a local Python script (scripts/analyze-competitor.py) to generate reports. This involves executing shell commands using user-provided inputs as arguments.
Audit Metadata