github-profile
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill defines an 'indirect prompt injection' surface in the 'Power Move' section, which directs the agent to fetch and analyze content from external URLs (github.com/[username]).
- Ingestion points: External data is ingested from a user-provided GitHub profile URL.
- Boundary markers: The provided prompt template does not use delimiters or instructions to ignore embedded commands within the analyzed profile.
- Capability inventory: The agent reads the profile data to generate recommendations and new README content.
- Sanitization: The skill does not include instructions for the agent to sanitize or validate the external content before processing.
Audit Metadata