00-andruia-consultant
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the local workspace to perform its diagnosis.
- Ingestion points: The agent scans files such as
package.json, source code insrc/, and existing documentation to determine the project's technical stack and debt. - Boundary markers: The instructions do not specify explicit delimiters or "ignore" markers for the content being read.
- Capability inventory: The skill is authorized to read local files and write results to local markdown files (
tareas.md,plan_implementacion.md). It does not demonstrate network or subprocess execution capabilities in the provided code. - Sanitization: No explicit sanitization or validation of the ingested file content is mentioned.
- [SAFE]: The skill references its source code on GitHub (
github.com/sickn33/agentic-awesome-skills). This is a transparent reference to the author's public repository and does not involve obfuscation or malicious redirection. - [SAFE]: The workflow involves standard project management activities, such as reading dependency manifests and drafting roadmaps, which match the stated purpose of the consultant tool.
Audit Metadata