readme
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from untrusted repository files (e.g.,
package.json,pyproject.toml,Cargo.toml, CI workflows, and existing README files) to generate or audit documentation. An attacker with write access to these files could embed malicious instructions to influence the agent's output. - Ingestion points: Repository metadata files, task runners (
Makefile,justfile), and CI configuration files (.github/workflows/). - Boundary markers: The skill does not provide explicit delimiters or instructions to ignore embedded prompts in the analyzed files.
- Capability inventory: The agent performs file reads and generates markdown output.
- Sanitization: No specific sanitization or validation of the input file content is performed.
- [SAFE]: The skill follows security best practices by directing the agent to read
.env.exampletemplates rather than actual sensitive.envfiles. - [SAFE]: The skill uses well-known and trusted services like Shields.io and GitHub for status badges and repository links.
Audit Metadata