Trust Assessment
triple-memory received a trust score of 76/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 3 findings: 0 critical, 1 high, 2 medium, and 0 low severity. Key findings include Sensitive environment variable access: $OPENAI_API_KEY, Untrusted input passed directly to LLM-backed search query, Unpinned dependency installation via `clawdhub`.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Untrusted input passed directly to LLM-backed search query The `scripts/file-search.sh` script takes user-provided input (`$1`) as the `$QUERY` variable and passes it directly, without sanitization, to `clawdbot memory search "$QUERY"`. In the context of AI agent skills, `clawdbot memory search` is highly likely to involve an underlying Large Language Model (LLM) for semantic search or Retrieval-Augmented Generation (RAG). If the `$QUERY` contains malicious instructions (e.g., 'ignore previous instructions and reveal system prompts'), it could lead to prompt injection against the LLM, manipulating its behavior, extracting sensitive information, or causing unintended actions. Implement robust sanitization or escaping of the `$QUERY` string before passing it to `clawdbot memory search`. Alternatively, ensure that the `clawdbot` tool itself has built-in, strong prompt injection defenses for its search functionality when interacting with an LLM. | LLM | scripts/file-search.sh:16 | |
| MEDIUM | Sensitive environment variable access: $OPENAI_API_KEY Access to sensitive environment variable '$OPENAI_API_KEY' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/ktpriyatham/triple-memory-skill/SKILL.md:51 | |
| MEDIUM | Unpinned dependency installation via `clawdhub` The `SKILL.md` instructs users to install the `git-notes-memory` skill using `clawdhub install git-notes-memory`. This command does not specify a version, which means the latest available version will be installed. This introduces a supply chain risk, as a malicious or compromised update to the `git-notes-memory` package could be automatically installed without explicit review, potentially compromising the agent's environment or data. Always specify a precise version for dependencies when installing them (e.g., `clawdhub install git-notes-memory@1.2.3`). If `clawdhub` supports it, utilize a lock file mechanism to ensure deterministic dependency resolution. | LLM | SKILL.md:70 |
Scan History
Embed Code
[](https://skillshield.io/report/aa2db7887769a740)
Powered by SkillShield