competitor-tracking
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch and analyze external data from GitHub and social listening tools, creating a surface for indirect prompt injection.
- Ingestion points: The skill utilizes the GitHub CLI (
gh) to search and retrieve content from issues and repository metadata. - Boundary markers: There are no instructions or delimiters defined to separate fetched external content from the agent's core instructions or to warn the agent about untrusted data.
- Capability inventory: The agent has access to execute shell commands via the
ghtool. - Sanitization: The skill lacks any explicit sanitization or filtering steps for the data retrieved from external platforms before it is analyzed by the agent.
Audit Metadata