working-on
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from local files (
DESCRIPTION,Project.toml,README.md) to extract titles and descriptions for the inventory. This creates a vulnerability where malicious instructions embedded in these files could influence the agent's behavior during the generation process. - Ingestion points: The agent reads the content of
DESCRIPTION,Project.toml, andREADME.mdfiles, and scans subdirectory names inSKILL.md. - Boundary markers: The instructions do not define delimiters or protective prompts to prevent the agent from obeying instructions found within the project files.
- Capability inventory: The agent has the capability to scan directories, read file contents, and write to a
CLAUDE.mdfile. - Sanitization: There is no evidence of sanitization or filtering to remove potential prompt injection payloads from the extracted text before it is processed or written to the output file.
Audit Metadata