build-plg-strategy
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and strategic frameworks, with no executable scripts, binaries, or automated shell commands detected.\n- [SAFE]: Analysis of the skill body and metadata reveals no evidence of obfuscation, hidden characters, or deceptive metadata.\n- [SAFE]: External URLs are limited to official amplitude.com blog posts and playbooks, which are verified vendor resources and do not represent a security risk.\n- [INDIRECT_PROMPT_INJECTION]: The skill incorporates a data ingestion surface for processing user-supplied product information.\n
- Ingestion points: User context is ingested through the
$ARGUMENTSvariable inSKILL.md.\n - Boundary markers: There are no explicit delimiters or instructions to the agent to treat the
$ARGUMENTScontent as untrusted data.\n - Capability inventory: The skill possesses no tools or permissions for file system modification, network communication, or command execution.\n
- Sanitization: No sanitization or input validation is performed on the user-provided growth goals prior to interpolation.
Audit Metadata