github-profile-optimization
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a local script,
scripts/profile-audit.py, to collect metadata and content from GitHub user and organization profiles. - [EXTERNAL_DOWNLOADS]: The skill performs network operations to fetch data from the GitHub REST and GraphQL APIs. These requests target legitimate subdomains of a well-known service (
api.github.com) and are used to retrieve the public information necessary for the audit. - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external sources and processes it within the agent's context.
- Ingestion points: Untrusted data enters the agent context through the
scripts/profile-audit.pyscript, which retrieves the full text of a user's GitHub profile README and repository descriptions. - Boundary markers: The skill's instructions do not include boundary markers or delimiters (such as triple-quotes or XML tags) to separate the untrusted user content from the agent's instructions, nor do they include explicit warnings to the agent to ignore instructions embedded within the fetched text.
- Capability inventory: The skill has the ability to execute Python scripts, perform network operations to the GitHub API, and access general shell commands in its runtime environment.
- Sanitization: The skill does not perform any sanitization or filtering on the external content to remove or neutralize potentially malicious natural language instructions before the agent processes it for the scorecard report.
Audit Metadata