ship-learn-next
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has a significant attack surface for indirect prompt injection because its core functionality involves reading and analyzing untrusted data from external files (YouTube transcripts, articles, tutorials, and notes) provided by the user.
- Ingestion points: The skill uses the
Readtool to ingest content from user-specified file paths (e.g.,/path/to/content.txt) as described inSKILL.md(Step 1). - Boundary markers: There are no explicit instructions for the agent to use boundary markers or delimiters to isolate the external content from its own instructions, nor are there warnings to ignore potentially malicious embedded commands.
- Capability inventory: The skill possesses the
Readtool (to ingest data) and theWritetool (to save the generated plan files). This combination allows instructions embedded in a source document to potentially influence the content written to the file system. - Sanitization: The instructions do not include specific sanitization, escaping, or filtering steps for the external content before it is processed or interpolated into the output plan.
Audit Metadata