stashr

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions heavily involve executing the stashr CLI tool to perform library operations such as searching, fetching content, and managing collections. These commands are restricted to the functionality of the Stashr service.
  • [EXTERNAL_DOWNLOADS]: The skill recommends that users install the @stashr/cli package globally using standard package managers (npm or bun). This is the primary dependency required for the skill's CLI transport method.
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection because its core functionality is to fetch and summarize external content (markdown) from a user's private bookmark library.
  • Ingestion points: External data enters the agent context via the search, get, and fetch_many tools/commands in SKILL.md.
  • Boundary markers: There are no instructions provided to use specific delimiters or to warn the agent to ignore potential instructions embedded within the retrieved bookmark text.
  • Capability inventory: The agent has the ability to execute shell commands (stashr CLI), write image previews to the filesystem (stashr media --output), and access the Stashr API over the network.
  • Sanitization: No specific sanitization or filtering steps are defined for the incoming bookmark content before it is processed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 02:53 PM
Security Audit — agent-trust-hub — stashr