postplan
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches content from external postplan.dev URLs using curl, creating a surface for malicious instructions to be ingested into the agent's context.
- Ingestion points: Remote HTML content fetched via curl as described in SKILL.md.
- Boundary markers: Absent; no delimiters or instructions to ignore embedded commands are specified.
- Capability inventory: Shell command execution (npx, curl) and local file writing.
- Sanitization: Absent; the skill does not include validation or filtering of remote content.
- [REMOTE_CODE_EXECUTION]: The skill executes npx postplan, which involves downloading and running an external package from the npm registry.
- [COMMAND_EXECUTION]: The skill relies on shell commands including npx and curl to perform its core functions.
- [DATA_EXFILTRATION]: The skill facilitates uploading content to postplan.dev, which results in publicly accessible URLs. While the skill includes warnings against including sensitive data, it provides a functional path for data exfiltration to a third-party service.
Audit Metadata