project-discovery
Warn
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: MEDIUMDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill includes explicit search patterns in
reference/search-patterns.mdto identify sensitive configuration files, specifically targeting.envand.env*files. Accessing these files represents a risk of exposing environment secrets and private credentials.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze potentially untrusted project data and documentation, which creates a surface for indirect prompt injection attacks.\n - Ingestion points: The workflow requires the agent to read project manifests (e.g.,
package.json), documentation (README.md), and source files to detect technology stacks and architecture.\n - Boundary markers: The instructions do not include specific delimiters or warnings to prevent the agent from obeying malicious instructions embedded within the analyzed project files.\n
- Capability inventory: The skill uses file system exploration and searching tools (
ls,grep) to gather information from the codebase.\n - Sanitization: There is no evidence of validation or sanitization of the content extracted from project files before it is processed.
Audit Metadata