The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses system commands such as mkdir to create directory structures for reports and cp to manage temporary data files.
[EXTERNAL_DOWNLOADS]: The skill utilizes curl to communicate with the external API endpoint mcp.sorftime.com to retrieve product details and review data. This is part of its core functionality.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection attacks.
Ingestion points: Untrusted data enters the agent context via Amazon product reviews fetched from the Sorftime API and stored in raw_reviews_sse.txt.
Boundary markers: None. The skill does not instruct the agent to use delimiters or ignore potential instructions embedded within the review text.
Capability inventory: The agent has the ability to read and write files and execute shell commands via the Bash, Read, and Write tools.
Sanitization: There is no evidence of filtering, escaping, or validation of the external review content before it is processed by the LLM.

review-analysis