supply-chain-risk-auditor
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from project dependency manifests and external GitHub repository metadata (such as READMEs and issue counts) using the
ghCLI andBash. - Ingestion points: Local dependency files (e.g.,
package.json,requirements.txt) and remote GitHub repository data fetched during the audit process. - Boundary markers: The instructions do not specify the use of delimiters or provide explicit warnings to the agent to disregard instructions embedded within the analyzed metadata.
- Capability inventory: The skill is granted access to the
Bash,Write,Read,Glob, andGreptools, which allows for shell command execution and local file system modification. - Sanitization: There are no instructions provided for sanitizing or escaping repository strings or retrieved metadata before they are used in shell commands or report generation.
Audit Metadata