developer-readme-design
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from repository files and uses it to update the README, which presents a surface for instructions embedded in source repositories to influence agent behavior.
- Ingestion points: In
SKILL.md, the workflow requires the agent to inspect the currentREADME.md, repository tree, and package manifests (e.g.,package.json). - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when the agent reads these external files.
- Capability inventory: The skill is granted the capability to directly update
README.mdand create new SVG files within the user's repository. - Sanitization: There is no explicit instruction to sanitize or filter potentially malicious prompt injection strings contained within the ingested repository data.
Audit Metadata