The Agent Skills Directory

[SAFE]: The skill follows security best practices and interacts only with official services.
Credential Handling: Instructions in references/environment-variables.md explicitly advise against committing secrets and recommend using secure platform mechanisms like environment groups and secret files.
Resource Access: The skill exclusively uses official vendor domains (render.com) and established, trusted Git providers (GitHub, GitLab, Bitbucket).
[INDIRECT_PROMPT_INJECTION]: The skill contains an ingestion surface for untrusted data by analyzing user codebase manifest files.
Ingestion points: Manifest files (e.g., package.json, requirements.txt, go.mod) are read during codebase analysis as specified in references/codebase-analysis.md.
Boundary markers: Absent; the skill does not define specific delimiters to isolate content from these files.
Capability inventory: The agent is authorized to execute git and render CLI commands based on the instructions in SKILL.md.
Sanitization: No explicit sanitization or filtering of manifest content is performed before processing.

render-deploy